https://github.com/beiyuouo/arxiv-daily

🎓 Automatically Update Some Fields Papers Daily using Github Actions (Update Every 12th hours)
https://github.com/beiyuouo/arxiv-daily

arxiv arxiv-api arxiv-daily arxiv-papers computer-vision federated-learning github-actions meta-learning robotics slam

Last synced: 3 months ago
JSON representation

🎓 Automatically Update Some Fields Papers Daily using Github Actions (Update Every 12th hours)

• Host: GitHub
• URL: https://github.com/beiyuouo/arxiv-daily
• Owner: beiyuouo
• License: mit
• Created: 2021-10-29T13:23:18.000Z (over 3 years ago)
• Default Branch: main
• Last Pushed: 2025-03-25T13:10:06.000Z (3 months ago)
• Last Synced: 2025-03-25T20:01:42.863Z (3 months ago)
• Topics: arxiv, arxiv-api, arxiv-daily, arxiv-papers, computer-vision, federated-learning, github-actions, meta-learning, robotics, slam
• Language: Python
• Homepage: https://www.bj-yan.top/arxiv-daily
• Size: 39.8 MB
• Stars: 164
• Watchers: 6
• Forks: 50
• Open Issues: 2
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# arxiv-daily

 Automated deployment @ 2025-04-04 09:21:31 Asia/Shanghai

> Welcome to contribute! Add your topics and keywords in [`topic.yml`](https://github.com/beiyuouo/arxiv-daily/blob/main/database/topic.yml).

> You can also view historical data through the [storage](https://github.com/beiyuouo/arxiv-daily/blob/main/database/storage).

## 3D Vision

### Point Cloud Registration

|Publish Date|Title|Authors|PDF|Code|

| :---: | :---: | :---: | :---: | :---: |

|**2025-04-02**|**Scene-Centric Unsupervised Panoptic Segmentation**|Oliver Hahn et.al.|[2504.01955v1](http://arxiv.org/abs/2504.01955v1)|null|

|**2025-04-02**|**Graphon games and an idealized limit of large network games**|Motoki Otsuka et.al.|[2504.01944v1](http://arxiv.org/abs/2504.01944v1)|null|

|**2025-04-02**|**Strengthening Multi-Robot Systems for SAR: Co-Designing Robotics and Communication Towards 6G**|Juan Bravo-Arrabal et.al.|[2504.01940v1](http://arxiv.org/abs/2504.01940v1)|null|

|**2025-04-02**|**Recovery Reductions in the Random Noise Model via Group Theory: Insights into NP-Complete and Fine-Grained Problems**|Tejas Nareddy et.al.|[2504.01899v1](http://arxiv.org/abs/2504.01899v1)|null|

|**2025-04-02**|**Synchro-curvature description of γ-ray light curves and spectra of pulsars: concurrent fitting**|Daniel Íñiguez-Pascual et.al.|[2504.01892v1](http://arxiv.org/abs/2504.01892v1)|null|

|**2025-04-02**|**Observing Spatial Charge and Spin Correlations in a Strongly-Interacting Fermi Gas**|Cyprien Daix et.al.|[2504.01885v1](http://arxiv.org/abs/2504.01885v1)|null|

|**2025-04-02**|**CO-DEFEND: Continuous Decentralized Federated Learning for Secure DoH-Based Threat Detection**|Diego Cajaraville-Aboy et.al.|[2504.01882v1](http://arxiv.org/abs/2504.01882v1)|null|

|**2025-04-02**|**Architect Your Landscape Approach (AYLA) for Optimizations in Deep Learning**|Ben Keslaki et.al.|[2504.01875v1](http://arxiv.org/abs/2504.01875v1)|null|

|**2025-04-02**|**Corner-Grasp: Multi-Action Grasp Detection and Active Gripper Adaptation for Grasping in Cluttered Environments**|Yeong Gwang Son et.al.|[2504.01861v1](http://arxiv.org/abs/2504.01861v1)|null|

|**2025-04-02**|**Many neighbors little entanglement: A curious scaling in the variable-range extended Ising model**|Harikrishnan K J et.al.|[2504.01846v1](http://arxiv.org/abs/2504.01846v1)|null|

|**2025-04-02**|**Dust environment of long-period comet C/2023 A3 (Tsuchinshan-ATLAS)**|Fernando Moreno et.al.|[2504.01845v1](http://arxiv.org/abs/2504.01845v1)|null|

|**2025-04-02**|**Detector Response to Gravitational Wave Polarizations in Gravitational Quantum Field Theory**|Cong Xu et.al.|[2504.01809v1](http://arxiv.org/abs/2504.01809v1)|null|

|**2025-04-02**|**US National Input to the European Strategy Update for Particle Physics**|André de Gouvêa et.al.|[2504.01804v1](http://arxiv.org/abs/2504.01804v1)|null|

|**2025-04-02**|**Distributed Triangle Detection is Hard in Few Rounds**|Sepehr Assadi et.al.|[2504.01802v1](http://arxiv.org/abs/2504.01802v1)|null|

|**2025-04-02**|**A New Approach to the Nonparametric Behrens-Fisher Problem with Compatible Confidence Intervals**|Stephen Schüürhuis et.al.|[2504.01796v1](http://arxiv.org/abs/2504.01796v1)|null|

|**2025-04-02**|**$\mathbf{γ^{(*)} + N(940)\frac{1}{2}^+ \to N(1520)\frac{3}{2}^{-}}$ helicity amplitudes and transition form factors**|Luis Albino et.al.|[2504.01770v1](http://arxiv.org/abs/2504.01770v1)|null|

|**2025-04-02**|**Dual-stream Transformer-GCN Model with Contextualized Representations Learning for Monocular 3D Human Pose Estimation**|Mingrui Ye et.al.|[2504.01764v1](http://arxiv.org/abs/2504.01764v1)|null|

|**2025-04-02**|**FIORD: A Fisheye Indoor-Outdoor Dataset with LIDAR Ground Truth for 3D Scene Reconstruction and Benchmarking**|Ulas Gunes et.al.|[2504.01732v1](http://arxiv.org/abs/2504.01732v1)|null|

|**2025-04-02**|**An Adaptive Proximal Inexact Gradient Framework and Its Application to Per-Antenna Constrained Joint Beamforming and Compression Design**|Xilai Fan et.al.|[2504.01721v1](http://arxiv.org/abs/2504.01721v1)|null|

|**2025-04-02**|**A two-player voting game in Euclidean space**|Stelios Stylianou et.al.|[2504.01713v1](http://arxiv.org/abs/2504.01713v1)|null|

|**2025-04-02**|**TransforMerger: Transformer-based Voice-Gesture Fusion for Robust Human-Robot Communication**|Petr Vanc et.al.|[2504.01708v1](http://arxiv.org/abs/2504.01708v1)|null|

|**2025-04-02**|**High-Order Flux Splitting Schemes for the Euler Equations of Gas Dynamics**|Shaoshuai Chu et.al.|[2504.01699v1](http://arxiv.org/abs/2504.01699v1)|null|

|**2025-04-02**|**Singularity-free cosmology from interactions in the dark sector**|Molly Burkmar et.al.|[2504.01683v1](http://arxiv.org/abs/2504.01683v1)|null|

|**2025-04-02**|**Introduction to dimensional reduction of fermions**|Joel Hutchinson et.al.|[2504.01670v1](http://arxiv.org/abs/2504.01670v1)|null|

|**2025-04-02**|**Overlap-Aware Feature Learning for Robust Unsupervised Domain Adaptation for 3D Semantic Segmentation**|Junjie Chen et.al.|[2504.01668v1](http://arxiv.org/abs/2504.01668v1)|null|

|**2025-04-02**|**Robust Unsupervised Domain Adaptation for 3D Point Cloud Segmentation Under Source Adversarial Attacks**|Haosheng Li et.al.|[2504.01659v2](http://arxiv.org/abs/2504.01659v2)|null|

|**2025-04-02**|**Sparse Gaussian Neural Processes**|Tommy Rochussen et.al.|[2504.01650v1](http://arxiv.org/abs/2504.01650v1)|null|

|**2025-04-02**|**ProtoGuard-guided PROPEL: Class-Aware Prototype Enhancement and Progressive Labeling for Incremental 3D Point Cloud Segmentation**|Haosheng Li et.al.|[2504.01648v1](http://arxiv.org/abs/2504.01648v1)|null|

|**2025-04-02**|**Bridge 2D-3D: Uncertainty-aware Hierarchical Registration Network with Domain Alignment**|Zhixin Cheng et.al.|[2504.01641v1](http://arxiv.org/abs/2504.01641v1)|null|

|**2025-04-02**|**On the performance of the Euler-Maruyama scheme for multidimensional SDEs with discontinuous drift coefficient**|Thomas Müller-Gronbach et.al.|[2504.01630v1](http://arxiv.org/abs/2504.01630v1)|null|

### Point Cloud Completion

|Publish Date|Title|Authors|PDF|Code|

| :---: | :---: | :---: | :---: | :---: |

|**2025-04-02**|**Scene-Centric Unsupervised Panoptic Segmentation**|Oliver Hahn et.al.|[2504.01955v1](http://arxiv.org/abs/2504.01955v1)|null|

|**2025-04-02**|**Graphon games and an idealized limit of large network games**|Motoki Otsuka et.al.|[2504.01944v1](http://arxiv.org/abs/2504.01944v1)|null|

|**2025-04-02**|**Strengthening Multi-Robot Systems for SAR: Co-Designing Robotics and Communication Towards 6G**|Juan Bravo-Arrabal et.al.|[2504.01940v1](http://arxiv.org/abs/2504.01940v1)|null|

|**2025-04-02**|**Sliding Dynamics of Skyrmion Molecular Crystals**|J. C. Bellizotti Souza et.al.|[2504.01923v1](http://arxiv.org/abs/2504.01923v1)|null|

|**2025-04-02**|**Recovery Reductions in the Random Noise Model via Group Theory: Insights into NP-Complete and Fine-Grained Problems**|Tejas Nareddy et.al.|[2504.01899v1](http://arxiv.org/abs/2504.01899v1)|null|

|**2025-04-02**|**Synchro-curvature description of γ-ray light curves and spectra of pulsars: concurrent fitting**|Daniel Íñiguez-Pascual et.al.|[2504.01892v1](http://arxiv.org/abs/2504.01892v1)|null|

|**2025-04-02**|**Observing Spatial Charge and Spin Correlations in a Strongly-Interacting Fermi Gas**|Cyprien Daix et.al.|[2504.01885v1](http://arxiv.org/abs/2504.01885v1)|null|

|**2025-04-02**|**CO-DEFEND: Continuous Decentralized Federated Learning for Secure DoH-Based Threat Detection**|Diego Cajaraville-Aboy et.al.|[2504.01882v1](http://arxiv.org/abs/2504.01882v1)|null|

|**2025-04-02**|**Architect Your Landscape Approach (AYLA) for Optimizations in Deep Learning**|Ben Keslaki et.al.|[2504.01875v1](http://arxiv.org/abs/2504.01875v1)|null|

|**2025-04-02**|**A Diffusion-Based Framework for Occluded Object Movement**|Zheng-Peng Duan et.al.|[2504.01873v1](http://arxiv.org/abs/2504.01873v1)|null|

|**2025-04-02**|**From Code Generation to Software Testing: AI Copilot with Context-Based RAG**|Yuchen Wang et.al.|[2504.01866v1](http://arxiv.org/abs/2504.01866v1)|null|

|**2025-04-02**|**Corner-Grasp: Multi-Action Grasp Detection and Active Gripper Adaptation for Grasping in Cluttered Environments**|Yeong Gwang Son et.al.|[2504.01861v1](http://arxiv.org/abs/2504.01861v1)|null|

|**2025-04-02**|**Many neighbors little entanglement: A curious scaling in the variable-range extended Ising model**|Harikrishnan K J et.al.|[2504.01846v1](http://arxiv.org/abs/2504.01846v1)|null|

|**2025-04-02**|**Dust environment of long-period comet C/2023 A3 (Tsuchinshan-ATLAS)**|Fernando Moreno et.al.|[2504.01845v1](http://arxiv.org/abs/2504.01845v1)|null|

|**2025-04-02**|**Cramér--Rao Inequalities for Several Generalized Fisher Information**|Hao Wu et.al.|[2504.01837v1](http://arxiv.org/abs/2504.01837v1)|null|

|**2025-04-02**|**Autonomous optical navigation for DESTINY+: Enhancing misalignment robustness in flyby observations with a rotating telescope**|Takayuki Hosonuma et.al.|[2504.01835v1](http://arxiv.org/abs/2504.01835v1)|null|

|**2025-04-02**|**Is Lorentz invariance violation found?**|Giorgio Galanti et.al.|[2504.01830v2](http://arxiv.org/abs/2504.01830v2)|null|

|**2025-04-02**|**Multiplexed Control at Scale for Electrode Arrays in Trapped-Ion Quantum Processors**|Ryutaro Ohira et.al.|[2504.01815v1](http://arxiv.org/abs/2504.01815v1)|null|

|**2025-04-02**|**Non-collocated vibration absorption using delayed resonator for spectral and spacial tuning -- analysis and experimental validation**|Matěj Kuře et.al.|[2504.01812v1](http://arxiv.org/abs/2504.01812v1)|null|

|**2025-04-02**|**Detector Response to Gravitational Wave Polarizations in Gravitational Quantum Field Theory**|Cong Xu et.al.|[2504.01809v1](http://arxiv.org/abs/2504.01809v1)|null|

|**2025-04-02**|**US National Input to the European Strategy Update for Particle Physics**|André de Gouvêa et.al.|[2504.01804v1](http://arxiv.org/abs/2504.01804v1)|null|

|**2025-04-02**|**Distributed Triangle Detection is Hard in Few Rounds**|Sepehr Assadi et.al.|[2504.01802v1](http://arxiv.org/abs/2504.01802v1)|null|

|**2025-04-02**|**A New Approach to the Nonparametric Behrens-Fisher Problem with Compatible Confidence Intervals**|Stephen Schüürhuis et.al.|[2504.01796v1](http://arxiv.org/abs/2504.01796v1)|null|

|**2025-04-02**|**$\mathbf{γ^{(*)} + N(940)\frac{1}{2}^+ \to N(1520)\frac{3}{2}^{-}}$ helicity amplitudes and transition form factors**|Luis Albino et.al.|[2504.01770v1](http://arxiv.org/abs/2504.01770v1)|null|

|**2025-04-02**|**Dual-stream Transformer-GCN Model with Contextualized Representations Learning for Monocular 3D Human Pose Estimation**|Mingrui Ye et.al.|[2504.01764v1](http://arxiv.org/abs/2504.01764v1)|null|

|**2025-04-02**|**Fully-gapped superconductivity with rotational symmetry breaking in pressurized kagome metal CsV$_3$Sb$_5$**|X. Y. Feng et.al.|[2504.01763v1](http://arxiv.org/abs/2504.01763v1)|null|

|**2025-04-02**|**Compact Group Homeomorphisms Preserving The Haar Measure**|Gang Liu et.al.|[2504.01760v1](http://arxiv.org/abs/2504.01760v1)|null|

|**2025-04-02**|**FIORD: A Fisheye Indoor-Outdoor Dataset with LIDAR Ground Truth for 3D Scene Reconstruction and Benchmarking**|Ulas Gunes et.al.|[2504.01732v1](http://arxiv.org/abs/2504.01732v1)|null|

|**2025-04-02**|**An Adaptive Proximal Inexact Gradient Framework and Its Application to Per-Antenna Constrained Joint Beamforming and Compression Design**|Xilai Fan et.al.|[2504.01721v1](http://arxiv.org/abs/2504.01721v1)|null|

|**2025-04-02**|**Construction of MDS Euclidean Self-Dual Codes via Multiple Subsets**|Weirong Meng et.al.|[2504.01717v1](http://arxiv.org/abs/2504.01717v1)|null|

### 3D Object Tracking

|Publish Date|Title|Authors|PDF|Code|

| :---: | :---: | :---: | :---: | :---: |

|**2025-04-02**|**Diffusion-Guided Gaussian Splatting for Large-Scale Unconstrained 3D Reconstruction and Novel View Synthesis**|Niluthpol Chowdhury Mithun et.al.|[2504.01960v1](http://arxiv.org/abs/2504.01960v1)|null|

|**2025-04-02**|**Slot-Level Robotic Placement via Visual Imitation from Single Human Video**|Dandan Shan et.al.|[2504.01959v1](http://arxiv.org/abs/2504.01959v1)|null|

|**2025-04-02**|**Toward Real-world BEV Perception: Depth Uncertainty Estimation via Gaussian Splatting**|Shu-Wei Lu et.al.|[2504.01957v2](http://arxiv.org/abs/2504.01957v2)|null|

|**2025-04-02**|**VideoScene: Distilling Video Diffusion Model to Generate 3D Scenes in One Step**|Hanyang Wang et.al.|[2504.01956v2](http://arxiv.org/abs/2504.01956v2)|null|

|**2025-04-02**|**Scene-Centric Unsupervised Panoptic Segmentation**|Oliver Hahn et.al.|[2504.01955v1](http://arxiv.org/abs/2504.01955v1)|null|

|**2025-04-02**|**Towards Unified Referring Expression Segmentation Across Omni-Level Visual Target Granularities**|Jing Liu et.al.|[2504.01954v1](http://arxiv.org/abs/2504.01954v1)|null|

|**2025-04-02**|**Gluing moduli spaces of quantum toric stacks via secondary fan**|Antoine Boivin et.al.|[2504.01945v1](http://arxiv.org/abs/2504.01945v1)|null|

|**2025-04-02**|**Strengthening Multi-Robot Systems for SAR: Co-Designing Robotics and Communication Towards 6G**|Juan Bravo-Arrabal et.al.|[2504.01940v1](http://arxiv.org/abs/2504.01940v1)|null|

|**2025-04-02**|**A Unified Approach to Analysis and Design of Denoising Markov Models**|Yinuo Ren et.al.|[2504.01938v1](http://arxiv.org/abs/2504.01938v1)|null|

|**2025-04-02**|**Critical Thinking: Which Kinds of Complexity Govern Optimal Reasoning Length?**|Celine Lee et.al.|[2504.01935v1](http://arxiv.org/abs/2504.01935v1)|null|

|**2025-04-02**|**Semidefinite lower bounds for covering codes**|Dion Gijswijt et.al.|[2504.01932v1](http://arxiv.org/abs/2504.01932v1)|null|

|**2025-04-02**|**Pairing Anderson motives via formal residues in the Frobenius endomorphism**|Quentin Gazda et.al.|[2504.01926v1](http://arxiv.org/abs/2504.01926v1)|null|

|**2025-04-02**|**Applying software engineering solutions to law management, Nigeria as a case study**|Chinonyerem Eleweke et.al.|[2504.01917v1](http://arxiv.org/abs/2504.01917v1)|null|

|**2025-04-02**|**Overcoming Deceptiveness in Fitness Optimization with Unsupervised Quality-Diversity**|Lisa Coiffard et.al.|[2504.01915v1](http://arxiv.org/abs/2504.01915v1)|null|

|**2025-04-02**|**Open cluster age calibration from colour-magnitude morphological indices using Gaia DR3 data**|F. A. Ferreira et.al.|[2504.01912v1](http://arxiv.org/abs/2504.01912v1)|null|

|**2025-04-02**|**Gaze-Hand Steering for Travel and Multitasking in Virtual Environments**|Mona Zavichi et.al.|[2504.01906v1](http://arxiv.org/abs/2504.01906v1)|null|

|**2025-04-02**|**Ross3D: Reconstructive Visual Instruction Tuning with 3D-Awareness**|Haochen Wang et.al.|[2504.01901v1](http://arxiv.org/abs/2504.01901v1)|null|

|**2025-04-02**|**A Diffusion-Based Framework for Occluded Object Movement**|Zheng-Peng Duan et.al.|[2504.01873v1](http://arxiv.org/abs/2504.01873v1)|null|

|**2025-04-02**|**CoMatcher: Multi-View Collaborative Feature Matching**|Jintao Zhang et.al.|[2504.01872v1](http://arxiv.org/abs/2504.01872v1)|null|

|**2025-04-02**|**Tidal interaction can stop galactic bars: on the LMC non-rotating bar**|Óscar Jiménez-Arranz et.al.|[2504.01870v1](http://arxiv.org/abs/2504.01870v1)|null|

|**2025-04-02**|**Buggin: Automatic intrinsic bugs classification model using NLP and ML**|Pragya Bhandari et.al.|[2504.01869v1](http://arxiv.org/abs/2504.01869v1)|null|

|**2025-04-02**|**Focal Mechanism Uncertainty Quantification In Ground Motion Simulations Of Le Teil Earthquake**|Valeria Soto et.al.|[2504.01868v1](http://arxiv.org/abs/2504.01868v1)|null|

|**2025-04-02**|**Extending MovieLens-32M to Provide New Evaluation Objectives**|Mark D. Smucker et.al.|[2504.01863v1](http://arxiv.org/abs/2504.01863v1)|null|

|**2025-04-02**|**Axiomatic Foundations of Fractal Analysis and Fractal Number Theory**|Stanislav Semenov et.al.|[2504.01862v1](http://arxiv.org/abs/2504.01862v1)|null|

|**2025-04-02**|**Corner-Grasp: Multi-Action Grasp Detection and Active Gripper Adaptation for Grasping in Cluttered Environments**|Yeong Gwang Son et.al.|[2504.01861v1](http://arxiv.org/abs/2504.01861v1)|null|

|**2025-04-02**|**Deciphering the Nature of Virgil: An Obscured AGN Lurking Within an Apparently Normal Lyman-α Emitter During Cosmic Reionization**|Pierluigi Rinaldi et.al.|[2504.01852v1](http://arxiv.org/abs/2504.01852v1)|null|

|**2025-04-02**|**Code Red! On the Harmfulness of Applying Off-the-shelf Large Language Models to Programming Tasks**|Ali Al-Kaswan et.al.|[2504.01850v1](http://arxiv.org/abs/2504.01850v1)|null|

|**2025-04-02**|**PaperBench: Evaluating AI's Ability to Replicate AI Research**|Giulio Starace et.al.|[2504.01848v1](http://arxiv.org/abs/2504.01848v1)|null|

|**2025-04-02**|**BOGausS: Better Optimized Gaussian Splatting**|Stéphane Pateux et.al.|[2504.01844v1](http://arxiv.org/abs/2504.01844v1)|null|

|**2025-04-02**|**Autonomous optical navigation for DESTINY+: Enhancing misalignment robustness in flyby observations with a rotating telescope**|Takayuki Hosonuma et.al.|[2504.01835v1](http://arxiv.org/abs/2504.01835v1)|null|

### Point Cloud

|Publish Date|Title|Authors|PDF|Code|

| :---: | :---: | :---: | :---: | :---: |

|**2025-04-02**|**Scene-Centric Unsupervised Panoptic Segmentation**|Oliver Hahn et.al.|[2504.01955v1](http://arxiv.org/abs/2504.01955v1)|null|

|**2025-04-02**|**Graphon games and an idealized limit of large network games**|Motoki Otsuka et.al.|[2504.01944v1](http://arxiv.org/abs/2504.01944v1)|null|

|**2025-04-02**|**Strengthening Multi-Robot Systems for SAR: Co-Designing Robotics and Communication Towards 6G**|Juan Bravo-Arrabal et.al.|[2504.01940v1](http://arxiv.org/abs/2504.01940v1)|null|

|**2025-04-02**|**Recovery Reductions in the Random Noise Model via Group Theory: Insights into NP-Complete and Fine-Grained Problems**|Tejas Nareddy et.al.|[2504.01899v1](http://arxiv.org/abs/2504.01899v1)|null|

|**2025-04-02**|**Synchro-curvature description of γ-ray light curves and spectra of pulsars: concurrent fitting**|Daniel Íñiguez-Pascual et.al.|[2504.01892v1](http://arxiv.org/abs/2504.01892v1)|null|

|**2025-04-02**|**Observing Spatial Charge and Spin Correlations in a Strongly-Interacting Fermi Gas**|Cyprien Daix et.al.|[2504.01885v1](http://arxiv.org/abs/2504.01885v1)|null|

|**2025-04-02**|**CO-DEFEND: Continuous Decentralized Federated Learning for Secure DoH-Based Threat Detection**|Diego Cajaraville-Aboy et.al.|[2504.01882v1](http://arxiv.org/abs/2504.01882v1)|null|

|**2025-04-02**|**Architect Your Landscape Approach (AYLA) for Optimizations in Deep Learning**|Ben Keslaki et.al.|[2504.01875v1](http://arxiv.org/abs/2504.01875v1)|null|

|**2025-04-02**|**Corner-Grasp: Multi-Action Grasp Detection and Active Gripper Adaptation for Grasping in Cluttered Environments**|Yeong Gwang Son et.al.|[2504.01861v1](http://arxiv.org/abs/2504.01861v1)|null|

|**2025-04-02**|**Many neighbors little entanglement: A curious scaling in the variable-range extended Ising model**|Harikrishnan K J et.al.|[2504.01846v1](http://arxiv.org/abs/2504.01846v1)|null|

|**2025-04-02**|**Dust environment of long-period comet C/2023 A3 (Tsuchinshan-ATLAS)**|Fernando Moreno et.al.|[2504.01845v1](http://arxiv.org/abs/2504.01845v1)|null|

|**2025-04-02**|**Detector Response to Gravitational Wave Polarizations in Gravitational Quantum Field Theory**|Cong Xu et.al.|[2504.01809v1](http://arxiv.org/abs/2504.01809v1)|null|

|**2025-04-02**|**US National Input to the European Strategy Update for Particle Physics**|André de Gouvêa et.al.|[2504.01804v1](http://arxiv.org/abs/2504.01804v1)|null|

|**2025-04-02**|**Distributed Triangle Detection is Hard in Few Rounds**|Sepehr Assadi et.al.|[2504.01802v1](http://arxiv.org/abs/2504.01802v1)|null|

|**2025-04-02**|**A New Approach to the Nonparametric Behrens-Fisher Problem with Compatible Confidence Intervals**|Stephen Schüürhuis et.al.|[2504.01796v1](http://arxiv.org/abs/2504.01796v1)|null|

|**2025-04-02**|**$\mathbf{γ^{(*)} + N(940)\frac{1}{2}^+ \to N(1520)\frac{3}{2}^{-}}$ helicity amplitudes and transition form factors**|Luis Albino et.al.|[2504.01770v1](http://arxiv.org/abs/2504.01770v1)|null|

|**2025-04-02**|**Dual-stream Transformer-GCN Model with Contextualized Representations Learning for Monocular 3D Human Pose Estimation**|Mingrui Ye et.al.|[2504.01764v1](http://arxiv.org/abs/2504.01764v1)|null|

|**2025-04-02**|**FIORD: A Fisheye Indoor-Outdoor Dataset with LIDAR Ground Truth for 3D Scene Reconstruction and Benchmarking**|Ulas Gunes et.al.|[2504.01732v1](http://arxiv.org/abs/2504.01732v1)|null|

|**2025-04-02**|**An Adaptive Proximal Inexact Gradient Framework and Its Application to Per-Antenna Constrained Joint Beamforming and Compression Design**|Xilai Fan et.al.|[2504.01721v1](http://arxiv.org/abs/2504.01721v1)|null|

|**2025-04-02**|**A two-player voting game in Euclidean space**|Stelios Stylianou et.al.|[2504.01713v1](http://arxiv.org/abs/2504.01713v1)|null|

|**2025-04-02**|**TransforMerger: Transformer-based Voice-Gesture Fusion for Robust Human-Robot Communication**|Petr Vanc et.al.|[2504.01708v1](http://arxiv.org/abs/2504.01708v1)|null|

|**2025-04-02**|**High-Order Flux Splitting Schemes for the Euler Equations of Gas Dynamics**|Shaoshuai Chu et.al.|[2504.01699v1](http://arxiv.org/abs/2504.01699v1)|null|

|**2025-04-02**|**Singularity-free cosmology from interactions in the dark sector**|Molly Burkmar et.al.|[2504.01683v1](http://arxiv.org/abs/2504.01683v1)|null|

|**2025-04-02**|**Introduction to dimensional reduction of fermions**|Joel Hutchinson et.al.|[2504.01670v1](http://arxiv.org/abs/2504.01670v1)|null|

|**2025-04-02**|**Overlap-Aware Feature Learning for Robust Unsupervised Domain Adaptation for 3D Semantic Segmentation**|Junjie Chen et.al.|[2504.01668v1](http://arxiv.org/abs/2504.01668v1)|null|

|**2025-04-02**|**Robust Unsupervised Domain Adaptation for 3D Point Cloud Segmentation Under Source Adversarial Attacks**|Haosheng Li et.al.|[2504.01659v2](http://arxiv.org/abs/2504.01659v2)|null|

|**2025-04-02**|**Sparse Gaussian Neural Processes**|Tommy Rochussen et.al.|[2504.01650v1](http://arxiv.org/abs/2504.01650v1)|null|

|**2025-04-02**|**ProtoGuard-guided PROPEL: Class-Aware Prototype Enhancement and Progressive Labeling for Incremental 3D Point Cloud Segmentation**|Haosheng Li et.al.|[2504.01648v1](http://arxiv.org/abs/2504.01648v1)|null|

|**2025-04-02**|**Bridge 2D-3D: Uncertainty-aware Hierarchical Registration Network with Domain Alignment**|Zhixin Cheng et.al.|[2504.01641v1](http://arxiv.org/abs/2504.01641v1)|null|

|**2025-04-02**|**On the performance of the Euler-Maruyama scheme for multidimensional SDEs with discontinuous drift coefficient**|Thomas Müller-Gronbach et.al.|[2504.01630v1](http://arxiv.org/abs/2504.01630v1)|null|

### Point Cloud Matching

|Publish Date|Title|Authors|PDF|Code|

| :---: | :---: | :---: | :---: | :---: |

|**2025-04-02**|**Scene-Centric Unsupervised Panoptic Segmentation**|Oliver Hahn et.al.|[2504.01955v1](http://arxiv.org/abs/2504.01955v1)|null|

|**2025-04-02**|**Towards Unified Referring Expression Segmentation Across Omni-Level Visual Target Granularities**|Jing Liu et.al.|[2504.01954v1](http://arxiv.org/abs/2504.01954v1)|null|

|**2025-04-02**|**Nucleon scattering from lattice QCD**|Colin Morningstar et.al.|[2504.01950v1](http://arxiv.org/abs/2504.01950v1)|null|

|**2025-04-02**|**Graphon games and an idealized limit of large network games**|Motoki Otsuka et.al.|[2504.01944v1](http://arxiv.org/abs/2504.01944v1)|null|

|**2025-04-02**|**Strengthening Multi-Robot Systems for SAR: Co-Designing Robotics and Communication Towards 6G**|Juan Bravo-Arrabal et.al.|[2504.01940v1](http://arxiv.org/abs/2504.01940v1)|null|

|**2025-04-02**|**A Unified Approach to Analysis and Design of Denoising Markov Models**|Yinuo Ren et.al.|[2504.01938v1](http://arxiv.org/abs/2504.01938v1)|null|

|**2025-04-02**|**Semidefinite lower bounds for covering codes**|Dion Gijswijt et.al.|[2504.01932v1](http://arxiv.org/abs/2504.01932v1)|null|

|**2025-04-02**|**Overcoming Deceptiveness in Fitness Optimization with Unsupervised Quality-Diversity**|Lisa Coiffard et.al.|[2504.01915v1](http://arxiv.org/abs/2504.01915v1)|null|

|**2025-04-02**|**Recovery Reductions in the Random Noise Model via Group Theory: Insights into NP-Complete and Fine-Grained Problems**|Tejas Nareddy et.al.|[2504.01899v1](http://arxiv.org/abs/2504.01899v1)|null|

|**2025-04-02**|**Synchro-curvature description of γ-ray light curves and spectra of pulsars: concurrent fitting**|Daniel Íñiguez-Pascual et.al.|[2504.01892v1](http://arxiv.org/abs/2504.01892v1)|null|

|**2025-04-02**|**Observing Spatial Charge and Spin Correlations in a Strongly-Interacting Fermi Gas**|Cyprien Daix et.al.|[2504.01885v1](http://arxiv.org/abs/2504.01885v1)|null|

|**2025-04-02**|**CO-DEFEND: Continuous Decentralized Federated Learning for Secure DoH-Based Threat Detection**|Diego Cajaraville-Aboy et.al.|[2504.01882v1](http://arxiv.org/abs/2504.01882v1)|null|

|**2025-04-02**|**Architect Your Landscape Approach (AYLA) for Optimizations in Deep Learning**|Ben Keslaki et.al.|[2504.01875v1](http://arxiv.org/abs/2504.01875v1)|null|

|**2025-04-02**|**CoMatcher: Multi-View Collaborative Feature Matching**|Jintao Zhang et.al.|[2504.01872v1](http://arxiv.org/abs/2504.01872v1)|null|

|**2025-04-02**|**Corner-Grasp: Multi-Action Grasp Detection and Active Gripper Adaptation for Grasping in Cluttered Environments**|Yeong Gwang Son et.al.|[2504.01861v1](http://arxiv.org/abs/2504.01861v1)|null|

|**2025-04-02**|**Lower Bounds for Leader Election and Collective Coin Flipping, Revisited**|Eshan Chattopadhyay et.al.|[2504.01856v1](http://arxiv.org/abs/2504.01856v1)|null|

|**2025-04-02**|**Many neighbors little entanglement: A curious scaling in the variable-range extended Ising model**|Harikrishnan K J et.al.|[2504.01846v1](http://arxiv.org/abs/2504.01846v1)|null|

|**2025-04-02**|**Dust environment of long-period comet C/2023 A3 (Tsuchinshan-ATLAS)**|Fernando Moreno et.al.|[2504.01845v1](http://arxiv.org/abs/2504.01845v1)|null|

|**2025-04-02**|**Non-collocated vibration absorption using delayed resonator for spectral and spacial tuning -- analysis and experimental validation**|Matěj Kuře et.al.|[2504.01812v1](http://arxiv.org/abs/2504.01812v1)|null|

|**2025-04-02**|**Detector Response to Gravitational Wave Polarizations in Gravitational Quantum Field Theory**|Cong Xu et.al.|[2504.01809v1](http://arxiv.org/abs/2504.01809v1)|null|

|**2025-04-02**|**US National Input to the European Strategy Update for Particle Physics**|André de Gouvêa et.al.|[2504.01804v1](http://arxiv.org/abs/2504.01804v1)|null|

|**2025-04-02**|**Distributed Triangle Detection is Hard in Few Rounds**|Sepehr Assadi et.al.|[2504.01802v1](http://arxiv.org/abs/2504.01802v1)|null|

|**2025-04-02**|**A New Approach to the Nonparametric Behrens-Fisher Problem with Compatible Confidence Intervals**|Stephen Schüürhuis et.al.|[2504.01796v1](http://arxiv.org/abs/2504.01796v1)|null|

|**2025-04-02**|**$\mathbf{γ^{(*)} + N(940)\frac{1}{2}^+ \to N(1520)\frac{3}{2}^{-}}$ helicity amplitudes and transition form factors**|Luis Albino et.al.|[2504.01770v1](http://arxiv.org/abs/2504.01770v1)|null|

|**2025-04-02**|**Dual-stream Transformer-GCN Model with Contextualized Representations Learning for Monocular 3D Human Pose Estimation**|Mingrui Ye et.al.|[2504.01764v1](http://arxiv.org/abs/2504.01764v1)|null|

|**2025-04-02**|**KD$^{2}$M: An unifying framework for feature knowledge distillation**|Eduardo Fernandes Montesuma et.al.|[2504.01757v1](http://arxiv.org/abs/2504.01757v1)|null|

|**2025-04-02**|**FIORD: A Fisheye Indoor-Outdoor Dataset with LIDAR Ground Truth for 3D Scene Reconstruction and Benchmarking**|Ulas Gunes et.al.|[2504.01732v1](http://arxiv.org/abs/2504.01732v1)|null|

|**2025-04-02**|**Brillouin-enhanced four-wave mixing with optical chiral states**|Xinglin Zeng et.al.|[2504.01725v1](http://arxiv.org/abs/2504.01725v1)|null|

|**2025-04-02**|**An Adaptive Proximal Inexact Gradient Framework and Its Application to Per-Antenna Constrained Joint Beamforming and Compression Design**|Xilai Fan et.al.|[2504.01721v1](http://arxiv.org/abs/2504.01721v1)|null|

|**2025-04-02**|**A two-player voting game in Euclidean space**|Stelios Stylianou et.al.|[2504.01713v1](http://arxiv.org/abs/2504.01713v1)|null|

### 3D Object Detection

|Publish Date|Title|Authors|PDF|Code|

| :---: | :---: | :---: | :---: | :---: |

|**2025-04-02**|**Diffusion-Guided Gaussian Splatting for Large-Scale Unconstrained 3D Reconstruction and Novel View Synthesis**|Niluthpol Chowdhury Mithun et.al.|[2504.01960v1](http://arxiv.org/abs/2504.01960v1)|null|

|**2025-04-02**|**Slot-Level Robotic Placement via Visual Imitation from Single Human Video**|Dandan Shan et.al.|[2504.01959v1](http://arxiv.org/abs/2504.01959v1)|null|

|**2025-04-02**|**Toward Real-world BEV Perception: Depth Uncertainty Estimation via Gaussian Splatting**|Shu-Wei Lu et.al.|[2504.01957v2](http://arxiv.org/abs/2504.01957v2)|null|

|**2025-04-02**|**VideoScene: Distilling Video Diffusion Model to Generate 3D Scenes in One Step**|Hanyang Wang et.al.|[2504.01956v2](http://arxiv.org/abs/2504.01956v2)|null|

|**2025-04-02**|**Scene-Centric Unsupervised Panoptic Segmentation**|Oliver Hahn et.al.|[2504.01955v1](http://arxiv.org/abs/2504.01955v1)|null|

|**2025-04-02**|**Towards Unified Referring Expression Segmentation Across Omni-Level Visual Target Granularities**|Jing Liu et.al.|[2504.01954v1](http://arxiv.org/abs/2504.01954v1)|null|

|**2025-04-02**|**Image Difference Grounding with Natural Language**|Wenxuan Wang et.al.|[2504.01952v1](http://arxiv.org/abs/2504.01952v1)|null|

|**2025-04-02**|**Gluing moduli spaces of quantum toric stacks via secondary fan**|Antoine Boivin et.al.|[2504.01945v1](http://arxiv.org/abs/2504.01945v1)|null|

|**2025-04-02**|**Strengthening Multi-Robot Systems for SAR: Co-Designing Robotics and Communication Towards 6G**|Juan Bravo-Arrabal et.al.|[2504.01940v1](http://arxiv.org/abs/2504.01940v1)|null|

|**2025-04-02**|**A Unified Approach to Analysis and Design of Denoising Markov Models**|Yinuo Ren et.al.|[2504.01938v1](http://arxiv.org/abs/2504.01938v1)|null|

|**2025-04-02**|**Semidefinite lower bounds for covering codes**|Dion Gijswijt et.al.|[2504.01932v1](http://arxiv.org/abs/2504.01932v1)|null|

|**2025-04-02**|**Pairing Anderson motives via formal residues in the Frobenius endomorphism**|Quentin Gazda et.al.|[2504.01926v1](http://arxiv.org/abs/2504.01926v1)|null|

|**2025-04-02**|**Is Less Really More? Fake News Detection with Limited Information**|Zhaoyang Cao et.al.|[2504.01922v1](http://arxiv.org/abs/2504.01922v1)|[link](https://github.com/kappakant/SLIM)|

|**2025-04-02**|**Applying software engineering solutions to law management, Nigeria as a case study**|Chinonyerem Eleweke et.al.|[2504.01917v1](http://arxiv.org/abs/2504.01917v1)|null|

|**2025-04-02**|**Overcoming Deceptiveness in Fitness Optimization with Unsupervised Quality-Diversity**|Lisa Coiffard et.al.|[2504.01915v1](http://arxiv.org/abs/2504.01915v1)|null|

|**2025-04-02**|**Open cluster age calibration from colour-magnitude morphological indices using Gaia DR3 data**|F. A. Ferreira et.al.|[2504.01912v1](http://arxiv.org/abs/2504.01912v1)|null|

|**2025-04-02**|**Build Code Needs Maintenance Too: A Study on Refactoring and Technical Debt in Build Systems**|Anwar Ghammam et.al.|[2504.01907v1](http://arxiv.org/abs/2504.01907v1)|null|

|**2025-04-02**|**Accelerating IoV Intrusion Detection: Benchmarking GPU-Accelerated vs CPU-Based ML Libraries**|Furkan Çolhak et.al.|[2504.01905v2](http://arxiv.org/abs/2504.01905v2)|null|

|**2025-04-02**|**Graphically Speaking: Unmasking Abuse in Social Media with Conversation Insights**|Célia Nouri et.al.|[2504.01902v1](http://arxiv.org/abs/2504.01902v1)|null|

|**2025-04-02**|**Ross3D: Reconstructive Visual Instruction Tuning with 3D-Awareness**|Haochen Wang et.al.|[2504.01901v1](http://arxiv.org/abs/2504.01901v1)|null|

|**2025-04-02**|**A minimal Pati-Salam theory: from cosmic defects to gravitational waves and colliders**|Goran Senjanović et.al.|[2504.01893v1](http://arxiv.org/abs/2504.01893v1)|null|

|**2025-04-02**|**Synchro-curvature description of γ-ray light curves and spectra of pulsars: concurrent fitting**|Daniel Íñiguez-Pascual et.al.|[2504.01892v1](http://arxiv.org/abs/2504.01892v1)|null|

|**2025-04-02**|**A novel gesture interaction control method for rehabilitation lower extremity exoskeleton**|Shuang Qiu et.al.|[2504.01888v1](http://arxiv.org/abs/2504.01888v1)|null|

|**2025-04-02**|**CO-DEFEND: Continuous Decentralized Federated Learning for Secure DoH-Based Threat Detection**|Diego Cajaraville-Aboy et.al.|[2504.01882v1](http://arxiv.org/abs/2504.01882v1)|null|

|**2025-04-02**|**A Diffusion-Based Framework for Occluded Object Movement**|Zheng-Peng Duan et.al.|[2504.01873v1](http://arxiv.org/abs/2504.01873v1)|null|

|**2025-04-02**|**CoMatcher: Multi-View Collaborative Feature Matching**|Jintao Zhang et.al.|[2504.01872v1](http://arxiv.org/abs/2504.01872v1)|null|

|**2025-04-02**|**Tidal interaction can stop galactic bars: on the LMC non-rotating bar**|Óscar Jiménez-Arranz et.al.|[2504.01870v1](http://arxiv.org/abs/2504.01870v1)|null|

|**2025-04-02**|**Buggin: Automatic intrinsic bugs classification model using NLP and ML**|Pragya Bhandari et.al.|[2504.01869v1](http://arxiv.org/abs/2504.01869v1)|null|

|**2025-04-02**|**Focal Mechanism Uncertainty Quantification In Ground Motion Simulations Of Le Teil Earthquake**|Valeria Soto et.al.|[2504.01868v1](http://arxiv.org/abs/2504.01868v1)|null|

|**2025-04-02**|**From Code Generation to Software Testing: AI Copilot with Context-Based RAG**|Yuchen Wang et.al.|[2504.01866v1](http://arxiv.org/abs/2504.01866v1)|null|

### Point Cloud Segmentation

|Publish Date|Title|Authors|PDF|Code|

| :---: | :---: | :---: | :---: | :---: |

|**2025-04-02**|**Scene-Centric Unsupervised Panoptic Segmentation**|Oliver Hahn et.al.|[2504.01955v1](http://arxiv.org/abs/2504.01955v1)|null|

|**2025-04-02**|**Towards Unified Referring Expression Segmentation Across Omni-Level Visual Target Granularities**|Jing Liu et.al.|[2504.01954v1](http://arxiv.org/abs/2504.01954v1)|null|

|**2025-04-02**|**Graphon games and an idealized limit of large network games**|Motoki Otsuka et.al.|[2504.01944v1](http://arxiv.org/abs/2504.01944v1)|null|

|**2025-04-02**|**Strengthening Multi-Robot Systems for SAR: Co-Designing Robotics and Communication Towards 6G**|Juan Bravo-Arrabal et.al.|[2504.01940v1](http://arxiv.org/abs/2504.01940v1)|null|

|**2025-04-02**|**Recovery Reductions in the Random Noise Model via Group Theory: Insights into NP-Complete and Fine-Grained Problems**|Tejas Nareddy et.al.|[2504.01899v1](http://arxiv.org/abs/2504.01899v1)|null|

|**2025-04-02**|**Synchro-curvature description of γ-ray light curves and spectra of pulsars: concurrent fitting**|Daniel Íñiguez-Pascual et.al.|[2504.01892v1](http://arxiv.org/abs/2504.01892v1)|null|

|**2025-04-02**|**Observing Spatial Charge and Spin Correlations in a Strongly-Interacting Fermi Gas**|Cyprien Daix et.al.|[2504.01885v1](http://arxiv.org/abs/2504.01885v1)|null|

|**2025-04-02**|**CO-DEFEND: Continuous Decentralized Federated Learning for Secure DoH-Based Threat Detection**|Diego Cajaraville-Aboy et.al.|[2504.01882v1](http://arxiv.org/abs/2504.01882v1)|null|

|**2025-04-02**|**Architect Your Landscape Approach (AYLA) for Optimizations in Deep Learning**|Ben Keslaki et.al.|[2504.01875v1](http://arxiv.org/abs/2504.01875v1)|null|

|**2025-04-02**|**Corner-Grasp: Multi-Action Grasp Detection and Active Gripper Adaptation for Grasping in Cluttered Environments**|Yeong Gwang Son et.al.|[2504.01861v1](http://arxiv.org/abs/2504.01861v1)|null|

|**2025-04-02**|**Many neighbors little entanglement: A curious scaling in the variable-range extended Ising model**|Harikrishnan K J et.al.|[2504.01846v1](http://arxiv.org/abs/2504.01846v1)|null|

|**2025-04-02**|**Dust environment of long-period comet C/2023 A3 (Tsuchinshan-ATLAS)**|Fernando Moreno et.al.|[2504.01845v1](http://arxiv.org/abs/2504.01845v1)|null|

|**2025-04-02**|**Detector Response to Gravitational Wave Polarizations in Gravitational Quantum Field Theory**|Cong Xu et.al.|[2504.01809v1](http://arxiv.org/abs/2504.01809v1)|null|

|**2025-04-02**|**US National Input to the European Strategy Update for Particle Physics**|André de Gouvêa et.al.|[2504.01804v1](http://arxiv.org/abs/2504.01804v1)|null|

|**2025-04-02**|**Distributed Triangle Detection is Hard in Few Rounds**|Sepehr Assadi et.al.|[2504.01802v1](http://arxiv.org/abs/2504.01802v1)|null|

|**2025-04-02**|**A New Approach to the Nonparametric Behrens-Fisher Problem with Compatible Confidence Intervals**|Stephen Schüürhuis et.al.|[2504.01796v1](http://arxiv.org/abs/2504.01796v1)|null|

|**2025-04-02**|**Time-optimal single-scalar control on a qubit of unitary dynamics**|Chungwei Lin et.al.|[2504.01785v1](http://arxiv.org/abs/2504.01785v1)|null|

|**2025-04-02**|**CLaP -- State Detection from Time Series**|Arik Ermshaus et.al.|[2504.01783v1](http://arxiv.org/abs/2504.01783v1)|null|

|**2025-04-02**|**$\mathbf{γ^{(*)} + N(940)\frac{1}{2}^+ \to N(1520)\frac{3}{2}^{-}}$ helicity amplitudes and transition form factors**|Luis Albino et.al.|[2504.01770v1](http://arxiv.org/abs/2504.01770v1)|null|

|**2025-04-02**|**Dual-stream Transformer-GCN Model with Contextualized Representations Learning for Monocular 3D Human Pose Estimation**|Mingrui Ye et.al.|[2504.01764v1](http://arxiv.org/abs/2504.01764v1)|null|

|**2025-04-02**|**FIORD: A Fisheye Indoor-Outdoor Dataset with LIDAR Ground Truth for 3D Scene Reconstruction and Benchmarking**|Ulas Gunes et.al.|[2504.01732v1](http://arxiv.org/abs/2504.01732v1)|null|

|**2025-04-02**|**An Adaptive Proximal Inexact Gradient Framework and Its Application to Per-Antenna Constrained Joint Beamforming and Compression Design**|Xilai Fan et.al.|[2504.01721v1](http://arxiv.org/abs/2504.01721v1)|null|

|**2025-04-02**|**A two-player voting game in Euclidean space**|Stelios Stylianou et.al.|[2504.01713v1](http://arxiv.org/abs/2504.01713v1)|null|

|**2025-04-02**|**TransforMerger: Transformer-based Voice-Gesture Fusion for Robust Human-Robot Communication**|Petr Vanc et.al.|[2504.01708v1](http://arxiv.org/abs/2504.01708v1)|null|

|**2025-04-02**|**High-Order Flux Splitting Schemes for the Euler Equations of Gas Dynamics**|Shaoshuai Chu et.al.|[2504.01699v1](http://arxiv.org/abs/2504.01699v1)|null|

|**2025-04-02**|**Segmentation variability and radiomics stability for predicting Triple-Negative Breast Cancer subtype using Magnetic Resonance Imaging**|Isabella Cama et.al.|[2504.01692v1](http://arxiv.org/abs/2504.01692v1)|null|

|**2025-04-02**|**Singularity-free cosmology from interactions in the dark sector**|Molly Burkmar et.al.|[2504.01683v1](http://arxiv.org/abs/2504.01683v1)|null|

|**2025-04-02**|**Introduction to dimensional reduction of fermions**|Joel Hutchinson et.al.|[2504.01670v1](http://arxiv.org/abs/2504.01670v1)|null|

|**2025-04-02**|**Overlap-Aware Feature Learning for Robust Unsupervised Domain Adaptation for 3D Semantic Segmentation**|Junjie Chen et.al.|[2504.01668v1](http://arxiv.org/abs/2504.01668v1)|null|

|**2025-04-02**|**Robust Unsupervised Domain Adaptation for 3D Point Cloud Segmentation Under Source Adversarial Attacks**|Haosheng Li et.al.|[2504.01659v2](http://arxiv.org/abs/2504.01659v2)|null|

## Computer Vision

### Instance Segmentation

|Publish Date|Title|Authors|PDF|Code|

| :---: | :---: | :---: | :---: | :---: |

|**2025-04-02**|**Scene-Centric Unsupervised Panoptic Segmentation**|Oliver Hahn et.al.|[2504.01955v1](http://arxiv.org/abs/2504.01955v1)|null|

|**2025-04-02**|**Towards Unified Referring Expression Segmentation Across Omni-Level Visual Target Granularities**|Jing Liu et.al.|[2504.01954v1](http://arxiv.org/abs/2504.01954v1)|null|

|**2025-04-02**|**Critical Thinking: Which Kinds of Complexity Govern Optimal Reasoning Length?**|Celine Lee et.al.|[2504.01935v1](http://arxiv.org/abs/2504.01935v1)|null|

|**2025-04-02**|**Is Less Really More? Fake News Detection with Limited Information**|Zhaoyang Cao et.al.|[2504.01922v1](http://arxiv.org/abs/2504.01922v1)|[link](https://github.com/kappakant/SLIM)|

|**2025-04-02**|**Recovery Reductions in the Random Noise Model via Group Theory: Insights into NP-Complete and Fine-Grained Problems**|Tejas Nareddy et.al.|[2504.01899v1](http://arxiv.org/abs/2504.01899v1)|null|

|**2025-04-02**|**DISINFOX: an open-source threat exchange platform serving intelligence on disinformation and influence operations**|Felipe Sánchez González et.al.|[2504.01803v1](http://arxiv.org/abs/2504.01803v1)|null|

|**2025-04-02**|**Time-optimal single-scalar control on a qubit of unitary dynamics**|Chungwei Lin et.al.|[2504.01785v1](http://arxiv.org/abs/2504.01785v1)|null|

|**2025-04-02**|**CLaP -- State Detection from Time Series**|Arik Ermshaus et.al.|[2504.01783v1](http://arxiv.org/abs/2504.01783v1)|null|

|**2025-04-02**|**Shared-Memory Hierarchical Process Mapping**|Christian Schulz et.al.|[2504.01726v1](http://arxiv.org/abs/2504.01726v1)|null|

|**2025-04-02**|**Iterative Interpolation Schedules for Quantum Approximate Optimization Algorithm**|Anuj Apte et.al.|[2504.01694v1](http://arxiv.org/abs/2504.01694v1)|null|

|**2025-04-02**|**Segmentation variability and radiomics stability for predicting Triple-Negative Breast Cancer subtype using Magnetic Resonance Imaging**|Isabella Cama et.al.|[2504.01692v1](http://arxiv.org/abs/2504.01692v1)|null|

|**2025-04-02**|**Overlap-Aware Feature Learning for Robust Unsupervised Domain Adaptation for 3D Semantic Segmentation**|Junjie Chen et.al.|[2504.01668v1](http://arxiv.org/abs/2504.01668v1)|null|

|**2025-04-02**|**Robust Unsupervised Domain Adaptation for 3D Point Cloud Segmentation Under Source Adversarial Attacks**|Haosheng Li et.al.|[2504.01659v2](http://arxiv.org/abs/2504.01659v2)|null|

|**2025-04-02**|**Q-Adapt: Adapting LMM for Visual Quality Assessment with Progressive Instruction Tuning**|Yiting Lu et.al.|[2504.01655v1](http://arxiv.org/abs/2504.01655v1)|null|

|**2025-04-02**|**ProtoGuard-guided PROPEL: Class-Aware Prototype Enhancement and Progressive Labeling for Incremental 3D Point Cloud Segmentation**|Haosheng Li et.al.|[2504.01648v1](http://arxiv.org/abs/2504.01648v1)|null|

|**2025-04-02**|**Dataset and Methodology for Material Identification and virtual s-SNOM Using AFM Phase Approach Curves**|Stefan R. Anton et.al.|[2504.01636v1](http://arxiv.org/abs/2504.01636v1)|null|

|**2025-04-02**|**Benchmarking the Spatial Robustness of DNNs via Natural and Adversarial Localized Corruptions**|Giulia Marchiori Pietrosanti et.al.|[2504.01632v1](http://arxiv.org/abs/2504.01632v1)|null|

|**2025-04-02**|**The Mini-SiTian Array: the mini-SiTian Realtime Image Processing pipeline (STRIP)**|Hongrui Gu et.al.|[2504.01609v1](http://arxiv.org/abs/2504.01609v1)|null|

|**2025-04-02**|**SpikeSift: A Computationally Efficient and Drift-Resilient Spike Sorting Algorithm**|Vasileios Georgiadis et.al.|[2504.01604v1](http://arxiv.org/abs/2504.01604v1)|null|

|**2025-04-02**|**A topology-preserving three-stage framework for fully-connected coronary artery extraction**|Yuehui Qiu et.al.|[2504.01597v1](http://arxiv.org/abs/2504.01597v1)|null|

|**2025-04-02**|**Instance Migration Diffusion for Nuclear Instance Segmentation in Pathology**|Lirui Qi et.al.|[2504.01577v1](http://arxiv.org/abs/2504.01577v1)|null|

|**2025-04-02**|**Quantum Computing for Optimizing Aircraft Loading**|Ananth Kaushik et.al.|[2504.01567v1](http://arxiv.org/abs/2504.01567v1)|null|

|**2025-04-02**|**STPNet: Scale-aware Text Prompt Network for Medical Image Segmentation**|Dandan Shan et.al.|[2504.01561v1](http://arxiv.org/abs/2504.01561v1)|null|

|**2025-04-02**|**Optimizing Package Delivery with Quantum Annealers: Addressing Time-Windows and Simultaneous Pickup and Delivery**|Eneko Osaba et.al.|[2504.01560v1](http://arxiv.org/abs/2504.01560v1)|null|

|**2025-04-02**|**Bhakti: A Lightweight Vector Database Management System for Endowing Large Language Models with Semantic Search Capabilities and Memory**|Zihao Wu et.al.|[2504.01553v1](http://arxiv.org/abs/2504.01553v1)|null|

|**2025-04-02**|**Semi-Supervised Biomedical Image Segmentation via Diffusion Models and Teacher-Student Co-Training**|Luca Ciampi et.al.|[2504.01547v1](http://arxiv.org/abs/2504.01547v1)|null|

|**2025-04-02**|**Local Computation Algorithms for Knapsack: impossibility results, and how to avoid them**|Clément L. Canonne et.al.|[2504.01543v1](http://arxiv.org/abs/2504.01543v1)|null|

|**2025-04-02**|**From Smør-re-brød to Subwords: Training LLMs on Danish, One Morpheme at a Time**|Mikkel Wildner Kildeberg et.al.|[2504.01540v1](http://arxiv.org/abs/2504.01540v1)|null|

|**2025-04-02**|**Beyond Nearest Neighbor Interpolation in Data Augmentation**|Olivier Rukundo et.al.|[2504.01527v1](http://arxiv.org/abs/2504.01527v1)|null|

|**2025-04-02**|**Chain of Correction for Full-text Speech Recognition with Large Language Models**|Zhiyuan Tang et.al.|[2504.01519v1](http://arxiv.org/abs/2504.01519v1)|null|

### Multi-Object Tracking

|Publish Date|Title|Authors|PDF|Code|

| :---: | :---: | :---: | :---: | :---: |

|**2025-04-02**|**Diffusion-Guided Gaussian Splatting for Large-Scale Unconstrained 3D Reconstruction and Novel View Synthesis**|Niluthpol Chowdhury Mithun et.al.|[2504.01960v1](http://arxiv.org/abs/2504.01960v1)|null|

|**2025-04-02**|**Slot-Level Robotic Placement via Visual Imitation from Single Human Video**|Dandan Shan et.al.|[2504.01959v1](http://arxiv.org/abs/2504.01959v1)|null|

|**2025-04-02**|**Toward Real-world BEV Perception: Depth Uncertainty Estimation via Gaussian Splatting**|Shu-Wei Lu et.al.|[2504.01957v2](http://arxiv.org/abs/2504.01957v2)|null|

|**2025-04-02**|**VideoScene: Distilling Video Diffusion Model to Generate 3D Scenes in One Step**|Hanyang Wang et.al.|[2504.01956v2](http://arxiv.org/abs/2504.01956v2)|null|

|**2025-04-02**|**Scene-Centric Unsupervised Panoptic Segmentation**|Oliver Hahn et.al.|[2504.01955v1](http://arxiv.org/abs/2504.01955v1)|null|

|**2025-04-02**|**Towards Unified Referring Expression Segmentation Across Omni-Level Visual Target Granularities**|Jing Liu et.al.|[2504.01954v1](http://arxiv.org/abs/2504.01954v1)|null|

|**2025-04-02**|**Image Difference Grounding with Natural Language**|Wenxuan Wang et.al.|[2504.01952v1](http://arxiv.org/abs/2504.01952v1)|null|

|**2025-04-02**|**Gluing moduli spaces of quantum toric stacks via secondary fan**|Antoine Boivin et.al.|[2504.01945v1](http://arxiv.org/abs/2504.01945v1)|null|

|**2025-04-02**|**A Unified Approach to Analysis and Design of Denoising Markov Models**|Yinuo Ren et.al.|[2504.01938v1](http://arxiv.org/abs/2504.01938v1)|null|

|**2025-04-02**|**Critical Thinking: Which Kinds of Complexity Govern Optimal Reasoning Length?**|Celine Lee et.al.|[2504.01935v1](http://arxiv.org/abs/2504.01935v1)|null|

|**2025-04-02**|**ILLUME+: Illuminating Unified MLLM with Dual Visual Tokenization and Diffusion Refinement**|Runhui Huang et.al.|[2504.01934v2](http://arxiv.org/abs/2504.01934v2)|null|

|**2025-04-02**|**Semidefinite lower bounds for covering codes**|Dion Gijswijt et.al.|[2504.01932v1](http://arxiv.org/abs/2504.01932v1)|null|

|**2025-04-02**|**Pairing Anderson motives via formal residues in the Frobenius endomorphism**|Quentin Gazda et.al.|[2504.01926v1](http://arxiv.org/abs/2504.01926v1)|null|

|**2025-04-02**|**Applying software engineering solutions to law management, Nigeria as a case study**|Chinonyerem Eleweke et.al.|[2504.01917v1](http://arxiv.org/abs/2504.01917v1)|null|

|**2025-04-02**|**FineLIP: Extending CLIP's Reach via Fine-Grained Alignment with Longer Text Inputs**|Mothilal Asokan et.al.|[2504.01916v1](http://arxiv.org/abs/2504.01916v1)|null|

|**2025-04-02**|**Overcoming Deceptiveness in Fitness Optimization with Unsupervised Quality-Diversity**|Lisa Coiffard et.al.|[2504.01915v1](http://arxiv.org/abs/2504.01915v1)|null|

|**2025-04-02**|**Open cluster age calibration from colour-magnitude morphological indices using Gaia DR3 data**|F. A. Ferreira et.al.|[2504.01912v1](http://arxiv.org/abs/2504.01912v1)|null|

|**2025-04-02**|**Gaze-Hand Steering for Travel and Multitasking in Virtual Environments**|Mona Zavichi et.al.|[2504.01906v1](http://arxiv.org/abs/2504.01906v1)|null|

|**2025-04-02**|**Ross3D: Reconstructive Visual Instruction Tuning with 3D-Awareness**|Haochen Wang et.al.|[2504.01901v1](http://arxiv.org/abs/2504.01901v1)|null|

|**2025-04-02**|**A minimal Pati-Salam theory: from cosmic defects to gravitational waves and colliders**|Goran Senjanović et.al.|[2504.01893v1](http://arxiv.org/abs/2504.01893v1)|null|

|**2025-04-02**|**Is Temporal Prompting All We Need For Limited Labeled Action Recognition?**|Shreyank N Gowda et.al.|[2504.01890v1](http://arxiv.org/abs/2504.01890v1)|null|

|**2025-04-02**|**A novel gesture interaction control method for rehabilitation lower extremity exoskeleton**|Shuang Qiu et.al.|[2504.01888v1](http://arxiv.org/abs/2504.01888v1)|null|

|**2025-04-02**|**GMAI-VL-R1: Harnessing Reinforcement Learning for Multimodal Medical Reasoning**|Yanzhou Su et.al.|[2504.01886v1](http://arxiv.org/abs/2504.01886v1)|null|

|**2025-04-02**|**A Diffusion-Based Framework for Occluded Object Movement**|Zheng-Peng Duan et.al.|[2504.01873v1](http://arxiv.org/abs/2504.01873v1)|null|

|**2025-04-02**|**CoMatcher: Multi-View Collaborative Feature Matching**|Jintao Zhang et.al.|[2504.01872v1](http://arxiv.org/abs/2504.01872v1)|null|

|**2025-04-02**|**Tidal interaction can stop galactic bars: on the LMC non-rotating bar**|Óscar Jiménez-Arranz et.al.|[2504.01870v1](http://arxiv.org/abs/2504.01870v1)|null|

|**2025-04-02**|**Buggin: Automatic intrinsic bugs classification model using NLP and ML**|Pragya Bhandari et.al.|[2504.01869v1](http://arxiv.org/abs/2504.01869v1)|null|

|**2025-04-02**|**Extending MovieLens-32M to Provide New Evaluation Objectives**|Mark D. Smucker et.al.|[2504.01863v1](http://arxiv.org/abs/2504.01863v1)|null|

|**2025-04-02**|**Axiomatic Foundations of Fractal Analysis and Fractal Number Theory**|Stanislav Semenov et.al.|[2504.01862v1](http://arxiv.org/abs/2504.01862v1)|null|

|**2025-04-02**|**Corner-Grasp: Multi-Action Grasp Detection and Active Gripper Adaptation for Grasping in Cluttered Environments**|Yeong Gwang Son et.al.|[2504.01861v1](http://arxiv.org/abs/2504.01861v1)|null|

### Image Classification

|Publish Date|Title|Authors|PDF|Code|

| :---: | :---: | :---: | :---: | :---: |

|**2025-04-02**|**Toward Real-world BEV Perception: Depth Uncertainty Estimation via Gaussian Splatting**|Shu-Wei Lu et.al.|[2504.01957v2](http://arxiv.org/abs/2504.01957v2)|null|

|**2025-04-02**|**Scene-Centric Unsupervised Panoptic Segmentation**|Oliver Hahn et.al.|[2504.01955v1](http://arxiv.org/abs/2504.01955v1)|null|

|**2025-04-02**|**Towards Unified Referring Expression Segmentation Across Omni-Level Visual Target Granularities**|Jing Liu et.al.|[2504.01954v1](http://arxiv.org/abs/2504.01954v1)|null|

|**2025-04-02**|**Deep Representation Learning for Unsupervised Clustering of Myocardial Fiber Trajectories in Cardiac Diffusion Tensor Imaging**|Mohini Anand et.al.|[2504.01953v1](http://arxiv.org/abs/2504.01953v1)|null|

|**2025-04-02**|**Image Difference Grounding with Natural Language**|Wenxuan Wang et.al.|[2504.01952v1](http://arxiv.org/abs/2504.01952v1)|null|

|**2025-04-02**|**End-to-End Driving with Online Trajectory Evaluation via BEV World Model**|Yingyan Li et.al.|[2504.01941v1](http://arxiv.org/abs/2504.01941v1)|null|

|**2025-04-02**|**ILLUME+: Illuminating Unified MLLM with Dual Visual Tokenization and Diffusion Refinement**|Runhui Huang et.al.|[2504.01934v2](http://arxiv.org/abs/2504.01934v2)|null|

|**2025-04-02**|**A thorough benchmark of automatic text classification: From traditional approaches to large language models**|Washington Cunha et.al.|[2504.01930v1](http://arxiv.org/abs/2504.01930v1)|null|

|**2025-04-02**|**Equivariant Spherical CNNs for Accurate Fiber Orientation Distribution Estimation in Neonatal Diffusion MRI with Reduced Acquisition Time**|Haykel Snoussi et.al.|[2504.01925v1](http://arxiv.org/abs/2504.01925v1)|null|

|**2025-04-02**|**Is Less Really More? Fake News Detection with Limited Information**|Zhaoyang Cao et.al.|[2504.01922v1](http://arxiv.org/abs/2504.01922v1)|[link](https://github.com/kappakant/SLIM)|

|**2025-04-02**|**FineLIP: Extending CLIP's Reach via Fine-Grained Alignment with Longer Text Inputs**|Mothilal Asokan et.al.|[2504.01916v1](http://arxiv.org/abs/2504.01916v1)|null|

|**2025-04-02**|**Ross3D: Reconstructive Visual Instruction Tuning with 3D-Awareness**|Haochen Wang et.al.|[2504.01901v1](http://arxiv.org/abs/2504.01901v1)|null|

|**2025-04-02**|**GMAI-VL-R1: Harnessing Reinforcement Learning for Multimodal Medical Reasoning**|Yanzhou Su et.al.|[2504.01886v1](http://arxiv.org/abs/2504.01886v1)|null|

|**2025-04-02**|**CO-DEFEND: Continuous Decentralized Federated Learning for Secure DoH-Based Threat Detection**|Diego Cajaraville-Aboy et.al.|[2504.01882v1](http://arxiv.org/abs/2504.01882v1)|null|

|**2025-04-02**|**Architect Your Landscape Approach (AYLA) for Optimizations in Deep Learning**|Ben Keslaki et.al.|[2504.01875v1](http://arxiv.org/abs/2504.01875v1)|null|

|**2025-04-02**|**A Diffusion-Based Framework for Occluded Object Movement**|Zheng-Peng Duan et.al.|[2504.01873v1](http://arxiv.org/abs/2504.01873v1)|null|

|**2025-04-02**|**CoMatcher: Multi-View Collaborative Feature Matching**|Jintao Zhang et.al.|[2504.01872v1](http://arxiv.org/abs/2504.01872v1)|null|

|**2025-04-02**|**Buggin: Automatic intrinsic bugs classification model using NLP and ML**|Pragya Bhandari et.al.|[2504.01869v1](http://arxiv.org/abs/2504.01869v1)|null|

|**2025-04-02**|**Axiomatic Foundations of Fractal Analysis and Fractal Number Theory**|Stanislav Semenov et.al.|[2504.01862v1](http://arxiv.org/abs/2504.01862v1)|null|

|**2025-04-02**|**Corner-Grasp: Multi-Action Grasp Detection and Active Gripper Adaptation for Grasping in Cluttered Environments**|Yeong Gwang Son et.al.|[2504.01861v1](http://arxiv.org/abs/2504.01861v1)|null|

|**2025-04-02**|**Deciphering the Nature of Virgil: An Obscured AGN Lurking Within an Apparently Normal Lyman-α Emitter During Cosmic Reionization**|Pierluigi Rinaldi et.al.|[2504.01852v1](http://arxiv.org/abs/2504.01852v1)|null|

|**2025-04-02**|**Dust environment of long-period comet C/2023 A3 (Tsuchinshan-ATLAS)**|Fernando Moreno et.al.|[2504.01845v1](http://arxiv.org/abs/2504.01845v1)|null|

|**2025-04-02**|**A Randomized Zeroth-Order Hierarchical Framework for Heterogeneous Federated Learning**|Yuyang Qiu et.al.|[2504.01839v1](http://arxiv.org/abs/2504.01839v1)|null|

|**2025-04-02**|**Prompting Medical Vision-Language Models to Mitigate Diagnosis Bias by Generating Realistic Dermoscopic Images**|Nusrat Munia et.al.|[2504.01838v1](http://arxiv.org/abs/2504.01838v1)|null|

|**2025-04-02**|**Implicit Bias Injection Attacks against Text-to-Image Diffusion Models**|Huayang Huang et.al.|[2504.01819v1](http://arxiv.org/abs/2504.01819v1)|null|

|**2025-04-02**|**Motility and rotation of multi-timescale microswimmers in linear background flows**|Eamonn A. Gaffney et.al.|[2504.01800v1](http://arxiv.org/abs/2504.01800v1)|null|

|**2025-04-02**|**A Novel Approach To Implementing Knowledge Distillation In Tsetlin Machines**|Calvin Kinateder et.al.|[2504.01798v1](http://arxiv.org/abs/2504.01798v1)|null|

|**2025-04-02**|**UniViTAR: Unified Vision Transformer with Native Resolution**|Limeng Qiao et.al.|[2504.01792v1](http://arxiv.org/abs/2504.01792v1)|null|

|**2025-04-02**|**Projections from Furstenberg boundaries onto maximal flats and barycenter maps**|Michelle Bucher et.al.|[2504.01788v1](http://arxiv.org/abs/2504.01788v1)|null|

|**2025-04-02**|**CLaP -- State Detection from Time Series**|Arik Ermshaus et.al.|[2504.01783v1](http://arxiv.org/abs/2504.01783v1)|null|

### Object Tracking

|Publish Date|Title|Authors|PDF|Code|

| :---: | :---: | :---: | :---: | :---: |

|**2025-04-02**|**Diffusion-Guided Gaussian Splatting for Large-Scale Unconstrained 3D Reconstruction and Novel View Synthesis**|Niluthpol Chowdhury Mithun et.al.|[2504.01960v1](http://arxiv.org/abs/2504.01960v1)|null|

|**2025-04-02**|**Slot-Level Robotic Placement via Visual Imitation from Single Human Video**|Dandan Shan et.al.|[2504.01959v1](http://arxiv.org/abs/2504.01959v1)|null|

|**2025-04-02**|**Toward Real-world BEV Perception: Depth Uncertainty Estimation via Gaussian Splatting**|Shu-Wei Lu et.al.|[2504.01957v2](http://arxiv.org/abs/2504.01957v2)|null|

|**2025-04-02**|**Scene-Centric Unsupervised Panoptic Segmentation**|Oliver Hahn et.al.|[2504.01955v1](http://arxiv.org/abs/2504.01955v1)|null|

|**2025-04-02**|**Towards Unified Referring Expression Segmentation Across Omni-Level Visual Target Granularities**|Jing Liu et.al.|[2504.01954v1](http://arxiv.org/abs/2504.01954v1)|null|

|**2025-04-02**|**Gluing moduli spaces of quantum toric stacks via secondary fan**|Antoine Boivin et.al.|[2504.01945v1](http://arxiv.org/abs/2504.01945v1)|null|

|**2025-04-02**|**A Unified Approach to Analysis and Design of Denoising Markov Models**|Yinuo Ren et.al.|[2504.01938v1](http://arxiv.org/abs/2504.01938v1)|null|

|**2025-04-02**|**Critical Thinking: Which Kinds of Complexity Govern Optimal Reasoning Length?**|Celine Lee et.al.|[2504.01935v1](http://arxiv.org/abs/2504.01935v1)|null|

|**2025-04-02**|**Semidefinite lower bounds for covering codes**|Dion Gijswijt et.al.|[2504.01932v1](http://arxiv.org/abs/2504.01932v1)|null|

|**2025-04-02**|**Pairing Anderson motives via formal residues in the Frobenius endomorphism**|Quentin Gazda et.al.|[2504.01926v1](http://arxiv.org/abs/2504.01926v1)|null|

|**2025-04-02**|**Applying software engineering solutions to law management, Nigeria as a case study**|Chinonyerem Eleweke et.al.|[2504.01917v1](http://arxiv.org/abs/2504.01917v1)|null|

|**2025-04-02**|**Overcoming Deceptiveness in Fitness Optimization with Unsupervised Quality-Diversity**|Lisa Coiffard et.al.|[2504.01915v1](http://arxiv.org/abs/2504.01915v1)|null|

|**2025-04-02**|**Open cluster age calibration from colour-magnitude morphological indices using Gaia DR3 data**|F. A. Ferreira et.al.|[2504.01912v1](http://arxiv.org/abs/2504.01912v1)|null|

|**2025-04-02**|**Gaze-Hand Steering for Travel and Multitasking in Virtual Environments**|Mona Zavichi et.al.|[2504.01906v1](http://arxiv.org/abs/2504.01906v1)|null|

|**2025-04-02**|**A Diffusion-Based Framework for Occluded Object Movement**|Zheng-Peng Duan et.al.|[2504.01873v1](http://arxiv.org/abs/2504.01873v1)|null|

|**2025-04-02**|**CoMatcher: Multi-View Collaborative Feature Matching**|Jintao Zhang et.al.|[2504.01872v1](http://arxiv.org/abs/2504.01872v1)|null|

|**2025-04-02**|**Tidal interaction can stop galactic bars: on the LMC non-rotating bar**|Óscar Jiménez-Arranz et.al.|[2504.01870v1](http://arxiv.org/abs/2504.01870v1)|null|

|**2025-04-02**|**Buggin: Automatic intrinsic bugs classification model using NLP and ML**|Pragya Bhandari et.al.|[2504.01869v1](http://arxiv.org/abs/2504.01869v1)|null|

|**2025-04-02**|**Extending MovieLens-32M to Provide New Evaluation Objectives**|Mark D. Smucker et.al.|[2504.01863v1](http://arxiv.org/abs/2504.01863v1)|null|

|**2025-04-02**|**Axiomatic Foundations of Fractal Analysis and Fractal Number Theory**|Stanislav Semenov et.al.|[2504.01862v1](http://arxiv.org/abs/2504.01862v1)|null|

|**2025-04-02**|**Corner-Grasp: Multi-Action Grasp Detection and Active Gripper Adaptation for Grasping in Cluttered Environments**|Yeong Gwang Son et.al.|[2504.01861v1](http://arxiv.org/abs/2504.01861v1)|null|

|**2025-04-02**|**Deciphering the Nature of Virgil: An Obscured AGN Lurking Within an Apparently Normal Lyman-α Emitter During Cosmic Reionization**|Pierluigi Rinaldi et.al.|[2504.01852v1](http://arxiv.org/abs/2504.01852v1)|null|

|**2025-04-02**|**Code Red! On the Harmfulness of Applying Off-the-shelf Large Language Models to Programming Tasks**|Ali Al-Kaswan et.al.|[2504.01850v1](http://arxiv.org/abs/2504.01850v1)|null|

|**2025-04-02**|**PaperBench: Evaluating AI's Ability to Replicate AI Research**|Giulio Starace et.al.|[2504.01848v1](http://arxiv.org/abs/2504.01848v1)|null|

|**2025-04-02**|**Autonomous optical navigation for DESTINY+: Enhancing misalignment robustness in flyby observations with a rotating telescope**|Takayuki Hosonuma et.al.|[2504.01835v1](http://arxiv.org/abs/2504.01835v1)|null|

|**2025-04-02**|**Track and Trace: Automatically Uncovering Cross-chain Transactions in the Multi-blockchain Ecosystems**|Dan Lin et.al.|[2504.01822v1](http://arxiv.org/abs/2504.01822v1)|null|

|**2025-04-02**|**Budget-Feasible Contracts**|Michal Feldman et.al.|[2504.01773v1](http://arxiv.org/abs/2504.01773v1)|null|

|**2025-04-02**|**Updating the Ephemeris and Physical Properties of Five Long-period Transiting Exoplanets Using TESS and CHEOPS**|Suman Saha et.al.|[2504.01768v1](http://arxiv.org/abs/2504.01768v1)|null|

|**2025-04-02**|**Leveraging Embedding Techniques in Multimodal Machine Learning for Mental Illness Assessment**|Abdelrahaman A. Hassan et.al.|[2504.01767v1](http://arxiv.org/abs/2504.01767v1)|null|

|**2025-04-02**|**Linear Time Iterative Decoders for Hypergraph-Product and Lifted-Product Codes**|Asit Kumar Pradhan et.al.|[2504.01728v1](http://arxiv.org/abs/2504.01728v1)|null|

### Keypoint Detection

|Publish Date|Title|Authors|PDF|Code|

| :---: | :---: | :---: | :---: | :---: |

|**2025-04-02**|**A novel gesture interaction control method for rehabilitation lower extremity exoskeleton**|Shuang Qiu et.al.|[2504.01888v1](http://arxiv.org/abs/2504.01888v1)|null|

|**2025-04-02**|**A computational framework for evaluating tire-asphalt hysteretic friction including pavement roughness**|Ivana Ban et.al.|[2504.01511v1](http://arxiv.org/abs/2504.01511v1)|null|

|**2025-04-02**|**ForestVO: Enhancing Visual Odometry in Forest Environments through ForestGlue**|Thomas Pritchard et.al.|[2504.01261v1](http://arxiv.org/abs/2504.01261v1)|null|

|**2025-03-31**|**A machine learning platform for development of low flammability polymers**|Duy Nhat Phan et.al.|[2504.00223v1](http://arxiv.org/abs/2504.00223v1)|null|

|**2025-03-31**|**Leveraging Diffusion Model and Image Foundation Model for Improved Correspondence Matching in Coronary Angiography**|Lin Zhao et.al.|[2504.00191v1](http://arxiv.org/abs/2504.00191v1)|null|

|**2025-03-31**|**SuperEvent: Cross-Modal Learning of Event-based Keypoint Detection**|Yannick Burkhardt et.al.|[2504.00139v1](http://arxiv.org/abs/2504.00139v1)|null|

|**2025-03-31**|**CoMatch: Dynamic Covisibility-Aware Transformer for Bilateral Subpixel-Level Semi-Dense Image Matching**|Zizhuo Li et.al.|[2503.23925v1](http://arxiv.org/abs/2503.23925v1)|null|

|**2025-03-31**|**GLane3D : Detecting Lanes with Graph of 3D Keypoints**|Halil İbrahim Öztürk et.al.|[2503.23882v1](http://arxiv.org/abs/2503.23882v1)|null|

|**2025-03-31**|**LiM-Loc: Visual Localization with Dense and Accurate 3D Reference Maps Directly Corresponding 2D Keypoints to 3D LiDAR Point Clouds**|Masahiko Tsuji et.al.|[2503.23664v1](http://arxiv.org/abs/2503.23664v1)|null|

|**2025-03-30**|**Optimal Invariant Bases for Atomistic Machine Learning**|Alice E. A. Allen et.al.|[2503.23515v2](http://arxiv.org/abs/2503.23515v2)|[link](https://github.com/lanl/hippynn)|

|**2025-03-30**|**POINT$^{2}$: A Polymer Informatics Training and Testing Database**|Jiaxin Xu et.al.|[2503.23491v1](http://arxiv.org/abs/2503.23491v1)|[link](https://github.com/jiaxin-xu/point2)|

|**2025-03-29**|**Deep Visual Servoing of an Aerial Robot Using Keypoint Feature Extraction**|Shayan Sepahvand et.al.|[2503.23171v1](http://arxiv.org/abs/2503.23171v1)|null|

|**2025-03-29**|**SuperEIO: Self-Supervised Event Feature Learning for Event Inertial Odometry**|Peiyu Chen et.al.|[2503.22963v1](http://arxiv.org/abs/2503.22963v1)|[link](https://github.com/arclab-hku/supereio)|

|**2025-03-28**|**Quantitative characterization of hydrophobic agglomeration at different mixing intensities using a copula-based probabilistic modeling approach**|Niklas Eiermann et.al.|[2503.22422v1](http://arxiv.org/abs/2503.22422v1)|null|

|**2025-03-27**|**NeuroLIP: Interpretable and Fair Cross-Modal Alignment of fMRI and Phenotypic Text**|Yanting Yang et.al.|[2503.21964v1](http://arxiv.org/abs/2503.21964v1)|null|

|**2025-03-27**|**Flexible Moment-Invariant Bases from Irreducible Tensors**|Roxana Bujack et.al.|[2503.21939v2](http://arxiv.org/abs/2503.21939v2)|null|

|**2025-03-27**|**LOCORE: Image Re-ranking with Long-Context Sequence Modeling**|Zilin Xiao et.al.|[2503.21772v1](http://arxiv.org/abs/2503.21772v1)|[link](https://github.com/MrZilinXiao/LongContextReranker)|

|**2025-03-27**|**Statistical learning of structure-property relationships for transport in porous media, using hybrid AI modeling**|Somayeh Hosseinhashemi et.al.|[2503.21560v1](http://arxiv.org/abs/2503.21560v1)|null|

|**2025-03-27**|**Recurrent Feature Mining and Keypoint Mixup Padding for Category-Agnostic Pose Estimation**|Junjie Chen et.al.|[2503.21140v1](http://arxiv.org/abs/2503.21140v1)|[link](https://github.com/chenbys/fmmp)|

|**2025-03-26**|**ReverBERT: A State Space Model for Efficient Text-Driven Speech Style Transfer**|Michael Brown et.al.|[2503.20992v1](http://arxiv.org/abs/2503.20992v1)|null|

|**2025-03-26**|**Robust Flower Cluster Matching Using The Unscented Transform**|Andy Chu et.al.|[2503.20631v1](http://arxiv.org/abs/2503.20631v1)|null|

|**2025-03-26**|**Structure Identification of NDS with Descriptor Subsystems under Asynchronous, Non-Uniform, and Slow-Rate Sampling**|Yunxiang Ma et.al.|[2503.20319v1](http://arxiv.org/abs/2503.20319v1)|null|

|**2025-03-26**|**Incremental Object Keypoint Learning**|Mingfu Liang et.al.|[2503.20248v1](http://arxiv.org/abs/2503.20248v1)|null|

|**2025-03-26**|**Multimodal Image Matching based on Frequency-domain Information of Local Energy Response**|Meng Yang et.al.|[2503.20827v1](http://arxiv.org/abs/2503.20827v1)|null|

|**2025-03-25**|**The Great Rift in Physics**|Tim Maudlin et.al.|[2503.20067v1](http://arxiv.org/abs/2503.20067v1)|null|

|**2025-03-25**|**Towards Online Multi-Modal Social Interaction Understanding**|Xinpeng Li et.al.|[2503.19851v1](http://arxiv.org/abs/2503.19851v1)|[link](https://github.com/sampson-lee/onlinemmsi)|

|**2025-03-25**|**Unpaired Object-Level SAR-to-Optical Image Translation for Aircraft with Keypoints-Guided Diffusion Models**|Ruixi You et.al.|[2503.19798v1](http://arxiv.org/abs/2503.19798v1)|null|

|**2025-03-25**|**MM-LINS: a Multi-Map LiDAR-Inertial System for Over-Degenerate Environments**|Yongxin Ma et.al.|[2503.19506v1](http://arxiv.org/abs/2503.19506v1)|[link](https://github.com/lian-yue0515/MM-LINS)|

|**2025-03-25**|**Multiscale Feature Importance-based Bit Allocation for End-to-End Feature Coding for Machines**|Junle Liu et.al.|[2503.19278v1](http://arxiv.org/abs/2503.19278v1)|null|

|**2025-03-24**|**Stochastic ecohydrological perspective on semi-distributed rainfall-runoff dynamics**|Mark S. Bartlett et.al.|[2503.19220v1](http://arxiv.org/abs/2503.19220v1)|null|

### Object Detection

|Publish Date|Title|Authors|PDF|Code|

| :---: | :---: | :---: | :---: | :---: |

|**2025-04-02**|**Diffusion-Guided Gaussian Splatting for Large-Scale Unconstrained 3D Reconstruction and Novel View Synthesis**|Niluthpol Chowdhury Mithun et.al.|[2504.01960v1](http://arxiv.org/abs/2504.01960v1)|null|

|**2025-04-02**|**Slot-Level Robotic Placement via Visual Imitation from Single Human Video**|Dandan Shan et.al.|[2504.01959v1](http://arxiv.org/abs/2504.01959v1)|null|

|**2025-04-02**|**Toward Real-world BEV Perception: Depth Uncertainty Estimation via Gaussian Splatting**|Shu-Wei Lu et.al.|[2504.01957v2](http://arxiv.org/abs/2504.01957v2)|null|

|**2025-04-02**|**Scene-Centric Unsupervised Panoptic Segmentation**|Oliver Hahn et.al.|[2504.01955v1](http://arxiv.org/abs/2504.01955v1)|null|

|**2025-04-02**|**Towards Unified Referring Expression Segmentation Across Omni-Level Visual Target Granularities**|Jing Liu et.al.|[2504.01954v1](http://arxiv.org/abs/2504.01954v1)|null|

|**2025-04-02**|**Gluing moduli spaces of quantum toric stacks via secondary fan**|Antoine Boivin et.al.|[2504.01945v1](http://arxiv.org/abs/2504.01945v1)|null|

|**2025-04-02**|**A Unified Approach to Analysis and Design of Denoising Markov Models**|Yinuo Ren et.al.|[2504.01938v1](http://arxiv.org/abs/2504.01938v1)|null|

|**2025-04-02**|**Semidefinite lower bounds for covering codes**|Dion Gijswijt et.al.|[2504.01932v1](http://arxiv.org/abs/2504.01932v1)|null|

|**2025-04-02**|**Pairing Anderson motives via formal residues in the Frobenius endomorphism**|Quentin Gazda et.al.|[2504.01926v1](http://arxiv.org/abs/2504.01926v1)|null|

|**2025-04-02**|**Applying software engineering solutions to law management, Nigeria as a case study**|Chinonyerem Eleweke et.al.|[2504.01917v1](http://arxiv.org/abs/2504.01917v1)|null|

|**2025-04-02**|**Overcoming Deceptiveness in Fitness Optimization with Unsupervised Quality-Diversity**|Lisa Coiffard et.al.|[2504.01915v1](http://arxiv.org/abs/2504.01915v1)|null|

|**2025-04-02**|**Open cluster age calibration from colour-magnitude morphological indices using Gaia DR3 data**|F. A. Ferreira et.al.|[2504.01912v1](http://arxiv.org/abs/2504.01912v1)|null|

|**2025-04-02**|**A Diffusion-Based Framework for Occluded Object Movement**|Zheng-Peng Duan et.al.|[2504.01873v1](http://arxiv.org/abs/2504.01873v1)|null|

|**2025-04-02**|**Buggin: Automatic intrinsic bugs classification model using NLP and ML**|Pragya Bhandari et.al.|[2504.01869v1](http://arxiv.org/abs/2504.01869v1)|null|

|**2025-04-02**|**Extending MovieLens-32M to Provide New Evaluation Objectives**|Mark D. Smucker et.al.|[2504.01863v1](http://arxiv.org/abs/2504.01863v1)|null|

|**2025-04-02**|**Axiomatic Foundations of Fractal Analysis and Fractal Number Theory**|Stanislav Semenov et.al.|[2504.01862v1](http://arxiv.org/abs/2504.01862v1)|null|

|**2025-04-02**|**Corner-Grasp: Multi-Action Grasp Detection and Active Gripper Adaptation for Grasping in Cluttered Environments**|Yeong Gwang Son et.al.|[2504.01861v1](http://arxiv.org/abs/2504.01861v1)|null|

|**2025-04-02**|**Deciphering the Nature of Virgil: An Obscured AGN Lurking Within an Apparently Normal Lyman-α Emitter During Cosmic Reionization**|Pierluigi Rinaldi et.al.|[2504.01852v1](http://arxiv.org/abs/2504.01852v1)|null|

|**2025-04-02**|**PaperBench: Evaluating AI's Ability to Replicate AI Research**|Giulio Starace et.al.|[2504.01848v1](http://arxiv.org/abs/2504.01848v1)|null|

|**2025-04-02**|**Evidence of doubly OZI-suppressed decay $η_{c} \to ωφ$ in the radiative decay $J/ψ\to γη_{c}$**|BESIII Collaboration et.al.|[2504.01823v1](http://arxiv.org/abs/2504.01823v1)|null|

|**2025-04-02**|**Detector Response to Gravitational Wave Polarizations in Gravitational Quantum Field Theory**|Cong Xu et.al.|[2504.01809v1](http://arxiv.org/abs/2504.01809v1)|null|

|**2025-04-02**|**Budget-Feasible Contracts**|Michal Feldman et.al.|[2504.01773v1](http://arxiv.org/abs/2504.01773v1)|null|

|**2025-04-02**|**Updating the Ephemeris and Physical Properties of Five Long-period Transiting Exoplanets Using TESS and CHEOPS**|Suman Saha et.al.|[2504.01768v1](http://arxiv.org/abs/2504.01768v1)|null|

|**2025-04-02**|**Leveraging Embedding Techniques in Multimodal Machine Learning for Mental Illness Assessment**|Abdelrahaman A. Hassan et.al.|[2504.01767v1](http://arxiv.org/abs/2504.01767v1)|null|

|**2025-04-02**|**Linear Time Iterative Decoders for Hypergraph-Product and Lifted-Product Codes**|Asit Kumar Pradhan et.al.|[2504.01728v1](http://arxiv.org/abs/2504.01728v1)|null|

|**2025-04-02**|**An Adaptive Proximal Inexact Gradient Framework and Its Application to Per-Antenna Constrained Joint Beamforming and Compression Design**|Xilai Fan et.al.|[2504.01721v1](http://arxiv.org/abs/2504.01721v1)|null|

|**2025-04-02**|**Studies of Hadronic Showers in SND@LHC**|The SND@LHC Collaboration et.al.|[2504.01716v1](http://arxiv.org/abs/2504.01716v1)|null|

|**2025-04-02**|**TransforMerger: Transformer-based Voice-Gesture Fusion for Robust Human-Robot Communication**|Petr Vanc et.al.|[2504.01708v1](http://arxiv.org/abs/2504.01708v1)|null|

|**2025-04-02**|**Single-atom-at-a-time adsorption studies of $^{211}$Bi and its precursor $^{211}$Pb on SiO$_{2}$ surfaces**|Dominik Dietzel et.al.|[2504.01697v1](http://arxiv.org/abs/2504.01697v1)|null|

|**2025-04-02**|**MS_ATpV-FWI: Full Waveform Inversion based on Multi-scale Structural Similarity Index Measure and Anisotropic Total p-Variation Regularization**|Liangsheng He et.al.|[2504.01695v1](http://arxiv.org/abs/2504.01695v1)|null|

### Semantic Segmentation

|Publish Date|Title|Authors|PDF|Code|

| :---: | :---: | :---: | :---: | :---: |

|**2025-04-02**|**Scene-Centric Unsupervised Panoptic Segmentation**|Oliver Hahn et.al.|[2504.01955v1](http://arxiv.org/abs/2504.01955v1)|null|

|**2025-04-02**|**Towards Unified Referring Expression Segmentation Across Omni-Level Visual Target Granularities**|Jing Liu et.al.|[2504.01954v1](http://arxiv.org/abs/2504.01954v1)|null|

|**2025-04-02**|**ILLUME+: Illuminating Unified MLLM with Dual Visual Tokenization and Diffusion Refinement**|Runhui Huang et.al.|[2504.01934v2](http://arxiv.org/abs/2504.01934v2)|null|

|**2025-04-02**|**Cross-Lingual Consistency: A Novel Inference Framework for Advancing Reasoning in Large Language Models**|Zhiwei Yu et.al.|[2504.01857v1](http://arxiv.org/abs/2504.01857v1)|null|

|**2025-04-02**|**Implicit Bias Injection Attacks against Text-to-Image Diffusion Models**|Huayang Huang et.al.|[2504.01819v1](http://arxiv.org/abs/2504.01819v1)|null|

|**2025-04-02**|**Time-optimal single-scalar control on a qubit of unitary dynamics**|Chungwei Lin et.al.|[2504.01785v1](http://arxiv.org/abs/2504.01785v1)|null|

|**2025-04-02**|**CLaP -- State Detection from Time Series**|Arik Ermshaus et.al.|[2504.01783v1](http://arxiv.org/abs/2504.01783v1)|null|

|**2025-04-02**|**Understanding Cross-Model Perceptual Invariances Through Ensemble Metamers**|Lukas Boehm et.al.|[2504.01739v1](http://arxiv.org/abs/2504.01739v1)|null|

|**2025-04-02**|**Segmentation variability and radiomics stability for predicting Triple-Negative Breast Cancer subtype using Magnetic Resonance Imaging**|Isabella Cama et.al.|[2504.01692v1](http://arxiv.org/abs/2504.01692v1)|null|

|**2025-04-02**|**Overlap-Aware Feature Learning for Robust Unsupervised Domain Adaptation for 3D Semantic Segmentation**|Junjie Chen et.al.|[2504.01668v1](http://arxiv.org/abs/2504.01668v1)|null|

|**2025-04-02**|**Robust Unsupervised Domain Adaptation for 3D Point Cloud Segmentation Under Source Adversarial Attacks**|Haosheng Li et.al.|[2504.01659v2](http://arxiv.org/abs/2504.01659v2)|null|

|**2025-04-02**|**ProtoGuard-guided PROPEL: Class-Aware Prototype Enhancement and Progressive Labeling for Incremental 3D Point Cloud Segmentation**|Haosheng Li et.al.|[2504.01648v1](http://arxiv.org/abs/2504.01648v1)|null|

|**2025-04-02**|**Dataset and Methodology for Material Identification and virtual s-SNOM Using AFM Phase Approach Curves**|Stefan R. Anton et.al.|[2504.01636v1](http://arxiv.org/abs/2504.01636v1)|null|

|**2025-04-02**|**Benchmarking the Spatial Robustness of DNNs via Natural and Adversarial Localized Corruptions**|Giulia Marchiori Pietrosanti et.al.|[2504.01632v1](http://arxiv.org/abs/2504.01632v1)|null|

|**2025-04-02**|**Horizon Scans can be accelerated using novel information retrieval and artificial intelligence tools**|Lena Schmidt et.al.|[2504.01627v1](http://arxiv.org/abs/2504.01627v1)|null|

|**2025-04-02**|**Multi-Relation Graph-Kernel Strengthen Network for Graph-Level Clustering**|Renda Han et.al.|[2504.01605v1](http://arxiv.org/abs/2504.01605v1)|null|

|**2025-04-02**|**SpikeSift: A Computationally Efficient and Drift-Resilient Spike Sorting Algorithm**|Vasileios Georgiadis et.al.|[2504.01604v1](http://arxiv.org/abs/2504.01604v1)|null|

|**2025-04-02**|**A$^\text{T}$A: Adaptive Transformation Agent for Text-Guided Subject-Position Variable Background Inpainting**|Yizhe Tang et.al.|[2504.01603v1](http://arxiv.org/abs/2504.01603v1)|null|

|**2025-04-02**|**A topology-preserving three-stage framework for fully-connected coronary artery extraction**|Yuehui Qiu et.al.|[2504.01597v1](http://arxiv.org/abs/2504.01597v1)|null|

|**2025-04-02**|**Text Speaks Louder than Vision: ASCII Art Reveals Textual Biases in Vision-Language Models**|Zhaochen Wang et.al.|[2504.01589v1](http://arxiv.org/abs/2504.01589v1)|null|

|**2025-04-02**|**Instance Migration Diffusion for Nuclear Instance Segmentation in Pathology**|Lirui Qi et.al.|[2504.01577v1](http://arxiv.org/abs/2504.01577v1)|null|

|**2025-04-02**|**STPNet: Scale-aware Text Prompt Network for Medical Image Segmentation**|Dandan Shan et.al.|[2504.01561v1](http://arxiv.org/abs/2504.01561v1)|null|

|**2025-04-02**|**FastER: Fast On-Demand Entity Resolution in Property Graphs**|Shujing Wang et.al.|[2504.01557v1](http://arxiv.org/abs/2504.01557v1)|null|

|**2025-04-02**|**Bhakti: A Lightweight Vector Database Management System for Endowing Large Language Models with Semantic Search Capabilities and Memory**|Zihao Wu et.al.|[2504.01553v1](http://arxiv.org/abs/2504.01553v1)|null|

|**2025-04-02**|**Semi-Supervised Biomedical Image Segmentation via Diffusion Models and Teacher-Student Co-Training**|Luca Ciampi et.al.|[2504.01547v1](http://arxiv.org/abs/2504.01547v1)|null|

|**2025-04-02**|**Hyperbolic Diffusion Recommender Model**|Meng Yuan et.al.|[2504.01541v1](http://arxiv.org/abs/2504.01541v1)|null|

|**2025-04-02**|**From Smør-re-brød to Subwords: Training LLMs on Danish, One Morpheme at a Time**|Mikkel Wildner Kildeberg et.al.|[2504.01540v1](http://arxiv.org/abs/2504.01540v1)|null|

|**2025-04-02**|**Beyond Nearest Neighbor Interpolation in Data Augmentation**|Olivier Rukundo et.al.|[2504.01527v1](http://arxiv.org/abs/2504.01527v1)|null|

|**2025-04-02**|**Chain of Correction for Full-text Speech Recognition with Large Language Models**|Zhiyuan Tang et.al.|[2504.01519v1](http://arxiv.org/abs/2504.01519v1)|null|

|**2025-04-02**|**Training-free Dense-Aligned Diffusion Guidance for Modular Conditional Image Synthesis**|Zixuan Wang et.al.|[2504.01515v2](http://arxiv.org/abs/2504.01515v2)|null|

### Image Matching

|Publish Date|Title|Authors|PDF|Code|

| :---: | :---: | :---: | :---: | :---: |

|**2025-04-02**|**Toward Real-world BEV Perception: Depth Uncertainty Estimation via Gaussian Splatting**|Shu-Wei Lu et.al.|[2504.01957v2](http://arxiv.org/abs/2504.01957v2)|null|

|**2025-04-02**|**Scene-Centric Unsupervised Panoptic Segmentation**|Oliver Hahn et.al.|[2504.01955v1](http://arxiv.org/abs/2504.01955v1)|null|

|**2025-04-02**|**Towards Unified Referring Expression Segmentation Across Omni-Level Visual Target Granularities**|Jing Liu et.al.|[2504.01954v1](http://arxiv.org/abs/2504.01954v1)|null|

|**2025-04-02**|**Deep Representation Learning for Unsupervised Clustering of Myocardial Fiber Trajectories in Cardiac Diffusion Tensor Imaging**|Mohini Anand et.al.|[2504.01953v1](http://arxiv.org/abs/2504.01953v1)|null|

|**2025-04-02**|**Image Difference Grounding with Natural Language**|Wenxuan Wang et.al.|[2504.01952v1](http://arxiv.org/abs/2504.01952v1)|null|

|**2025-04-02**|**Nucleon scattering from lattice QCD**|Colin Morningstar et.al.|[2504.01950v1](http://arxiv.org/abs/2504.01950v1)|null|

|**2025-04-02**|**End-to-End Driving with Online Trajectory Evaluation via BEV World Model**|Yingyan Li et.al.|[2504.01941v1](http://arxiv.org/abs/2504.01941v1)|null|

|**2025-04-02**|**A Unified Approach to Analysis and Design of Denoising Markov Models**|Yinuo Ren et.al.|[2504.01938v1](http://arxiv.org/abs/2504.01938v1)|null|

|**2025-04-02**|**ILLUME+: Illuminating Unified MLLM with Dual Visual Tokenization and Diffusion Refinement**|Runhui Huang et.al.|[2504.01934v2](http://arxiv.org/abs/2504.01934v2)|null|

|**2025-04-02**|**Semidefinite lower bounds for covering codes**|Dion Gijswijt et.al.|[2504.01932v1](http://arxiv.org/abs/2504.01932v1)|null|

|**2025-04-02**|**Equivariant Spherical CNNs for Accurate Fiber Orientation Distribution Estimation in Neonatal Diffusion MRI with Reduced Acquisition Time**|Haykel Snoussi et.al.|[2504.01925v1](http://arxiv.org/abs/2504.01925v1)|null|

|**2025-04-02**|**Is Less Really More? Fake News Detection with Limited Information**|Zhaoyang Cao et.al.|[2504.01922v1](http://arxiv.org/abs/2504.01922v1)|[link](https://github.com/kappakant/SLIM)|

|**2025-04-02**|**FineLIP: Extending CLIP's Reach via Fine-Grained Alignment with Longer Text Inputs**|Mothilal Asokan et.al.|[2504.01916v1](http://arxiv.org/abs/2504.01916v1)|null|

|**2025-04-02**|**Overcoming Deceptiveness in Fitness Optimization with Unsupervised Quality-Diversity**|Lisa Coiffard et.al.|[2504.01915v1](http://arxiv.org/abs/2504.01915v1)|null|

|**2025-04-02**|**Ross3D: Reconstructive Visual Instruction Tuning with 3D-Awareness**|Haochen Wang et.al.|[2504.01901v1](http://arxiv.org/abs/2504.01901v1)|null|

|**2025-04-02**|**GMAI-VL-R1: Harnessing Reinforcement Learning for Multimodal Medical Reasoning**|Yanzhou Su et.al.|[2504.01886v1](http://arxiv.org/abs/2504.01886v1)|null|

|**2025-04-02**|**A Diffusion-Based Framework for Occluded Object Movement**|Zheng-Peng Duan et.al.|[2504.01873v1](http://arxiv.org/abs/2504.01873v1)|null|

|**2025-04-02**|**CoMatcher: Multi-View Collaborative Feature Matching**|Jintao Zhang et.al.|[2504.01872v1](http://arxiv.org/abs/2504.01872v1)|null|

|**2025-04-02**|**Corner-Grasp: Multi-Action Grasp Detection and Active Gripper Adaptation for Grasping in Cluttered Environments**|Yeong Gwang Son et.al.|[2504.01861v1](http://arxiv.org/abs/2504.01861v1)|null|

|**2025-04-02**|**Lower Bounds for Leader Election and Collective Coin Flipping, Revisited**|Eshan Chattopadhyay et.al.|[2504.01856v1](http://arxiv.org/abs/2504.01856v1)|null|

|**2025-04-02**|**Deciphering the Nature of Virgil: An Obscured AGN Lurking Within an Apparently Normal Lyman-α Emitter During Cosmic Reionization**|Pierluigi Rinaldi et.al.|[2504.01852v1](http://arxiv.org/abs/2504.01852v1)|null|

|**2025-04-02**|**Dust environment of long-period comet C/2023 A3 (Tsuchinshan-ATLAS)**|Fernando Moreno et.al.|[2504.01845v1](http://arxiv.org/abs/2504.01845v1)|null|

|**2025-04-02**|**A Randomized Zeroth-Order Hierarchical Framework for Heterogeneous Federated Learning**|Yuyang Qiu et.al.|[2504.01839v1](http://arxiv.org/abs/2504.01839v1)|null|

|**2025-04-02**|**Prompting Medical Vision-Language Models to Mitigate Diagnosis Bias by Generating Realistic Dermoscopic Images**|Nusrat Munia et.al.|[2504.01838v1](http://arxiv.org/abs/2504.01838v1)|null|

|**2025-04-02**|**Implicit Bias Injection Attacks against Text-to-Image Diffusion Models**|Huayang Huang et.al.|[2504.01819v1](http://arxiv.org/abs/2504.01819v1)|null|

|**2025-04-02**|**Non-collocated vibration absorption using delayed resonator for spectral and spacial tuning -- analysis and experimental validation**|Matěj Kuře et.al.|[2504.01812v1](http://arxiv.org/abs/2504.01812v1)|null|

|**2025-04-02**|**A Novel Approach To Implementing Knowledge Distillation In Tsetlin Machines**|Calvin Kinateder et.al.|[2504.01798v1](http://arxiv.org/abs/2504.01798v1)|null|

|**2025-04-02**|**UniViTAR: Unified Vision Transformer with Native Resolution**|Limeng Qiao et.al.|[2504.01792v1](http://arxiv.org/abs/2504.01792v1)|null|

|**2025-04-02**|**Projections from Furstenberg boundaries onto maximal flats and barycenter maps**|Michelle Bucher et.al.|[2504.01788v1](http://arxiv.org/abs/2504.01788v1)|null|

|**2025-04-02**|**Defect detection in III-V multijunction solar cells using reverse-bias stress tests**|Aitana Cano et.al.|[2504.01775v1](http://arxiv.org/abs/2504.01775v1)|null|

## Federated Learning

### Federated Learning

|Publish Date|Title|Authors|PDF|Code|

| :---: | :---: | :---: | :---: | :---: |

|**2025-04-02**|**Learning from Streaming Video with Orthogonal Gradients**|Tengda Han et.al.|[2504.01961v1](http://arxiv.org/abs/2504.01961v1)|null|

|**2025-04-02**|**Diffusion-Guided Gaussian Splatting for Large-Scale Unconstrained 3D Reconstruction and Novel View Synthesis**|Niluthpol Chowdhury Mithun et.al.|[2504.01960v1](http://arxiv.org/abs/2504.01960v1)|null|

|**2025-04-02**|**Slot-Level Robotic Placement via Visual Imitation from Single Human Video**|Dandan Shan et.al.|[2504.01959v1](http://arxiv.org/abs/2504.01959v1)|null|

|**2025-04-02**|**Toward Real-world BEV Perception: Depth Uncertainty Estimation via Gaussian Splatting**|Shu-Wei Lu et.al.|[2504.01957v2](http://arxiv.org/abs/2504.01957v2)|null|

|**2025-04-02**|**Deep Representation Learning for Unsupervised Clustering of Myocardial Fiber Trajectories in Cardiac Diffusion Tensor Imaging**|Mohini Anand et.al.|[2504.01953v1](http://arxiv.org/abs/2504.01953v1)|null|

|**2025-04-02**|**Efficient Federated Learning Tiny Language Models for Mobile Network Feature Prediction**|Daniel Becking et.al.|[2504.01947v1](http://arxiv.org/abs/2504.01947v1)|null|

|**2025-04-02**|**OpenCodeReasoning: Advancing Data Distillation for Competitive Coding**|Wasi Uddin Ahmad et.al.|[2504.01943v1](http://arxiv.org/abs/2504.01943v1)|null|

|**2025-04-02**|**Strengthening Multi-Robot Systems for SAR: Co-Designing Robotics and Communication Towards 6G**|Juan Bravo-Arrabal et.al.|[2504.01940v1](http://arxiv.org/abs/2504.01940v1)|null|

|**2025-04-02**|**A Unified Approach to Analysis and Design of Denoising Markov Models**|Yinuo Ren et.al.|[2504.01938v1](http://arxiv.org/abs/2504.01938v1)|null|

|**2025-04-02**|**Fermionic Averaged Circuit Eigenvalue Sampling**|Adrian Chapman et.al.|[2504.01936v1](http://arxiv.org/abs/2504.01936v1)|null|

|**2025-04-02**|**Hessian-aware Training for Enhancing DNNs Resilience to Parameter Corruptions**|Tahmid Hasan Prato et.al.|[2504.01933v1](http://arxiv.org/abs/2504.01933v1)|null|

|**2025-04-02**|**Is the Reversal Curse a Binding Problem? Uncovering Limitations of Transformers from a Basic Generalization Failure**|Boshi Wang et.al.|[2504.01928v1](http://arxiv.org/abs/2504.01928v1)|null|

|**2025-04-02**|**Gen-C: Populating Virtual Worlds with Generative Crowds**|Andreas Panayiotou et.al.|[2504.01924v1](http://arxiv.org/abs/2504.01924v1)|null|

|**2025-04-02**|**Client Selection in Federated Learning with Data Heterogeneity and Network Latencies**|Harsh Vardhan et.al.|[2504.01921v1](http://arxiv.org/abs/2504.01921v1)|null|

|**2025-04-02**|**Bridging the Linguistic Divide: A Survey on Leveraging Large Language Models for Machine Translation**|Baban Gain et.al.|[2504.01919v2](http://arxiv.org/abs/2504.01919v2)|null|

|**2025-04-02**|**Overcoming Deceptiveness in Fitness Optimization with Unsupervised Quality-Diversity**|Lisa Coiffard et.al.|[2504.01915v1](http://arxiv.org/abs/2504.01915v1)|null|

|**2025-04-02**|**Representing Flow Fields with Divergence-Free Kernels for Reconstruction**|Xingyu Ni et.al.|[2504.01913v1](http://arxiv.org/abs/2504.01913v1)|null|

|**2025-04-02**|**Benchmarking Synthetic Tabular Data: A Multi-Dimensional Evaluation Framework**|Andrey Sidorenko et.al.|[2504.01908v1](http://arxiv.org/abs/2504.01908v1)|[link](https://github.com/mostly-ai/mostlyai-qa)|

|**2025-04-02**|**Accelerating IoV Intrusion Detection: Benchmarking GPU-Accelerated vs CPU-Based ML Libraries**|Furkan Çolhak et.al.|[2504.01905v2](http://arxiv.org/abs/2504.01905v2)|null|

|**2025-04-02**|**Graphically Speaking: Unmasking Abuse in Social Media with Conversation Insights**|Célia Nouri et.al.|[2504.01902v1](http://arxiv.org/abs/2504.01902v1)|null|

|**2025-04-02**|**Analysis of an Idealized Stochastic Polyak Method and its Application to Black-Box Model Distillation**|Robert M. Gower et.al.|[2504.01898v1](http://arxiv.org/abs/2504.01898v1)|null|

|**2025-04-02**|**Composition Design of Shape Memory Ceramics based on Gaussian Processes**|Ashutosh Pandey et.al.|[2504.01896v1](http://arxiv.org/abs/2504.01896v1)|null|

|**2025-04-02**|**Multi-fidelity Parameter Estimation Using Conditional Diffusion Models**|Caroline Tatsuoka et.al.|[2504.01894v1](http://arxiv.org/abs/2504.01894v1)|null|

|**2025-04-02**|**Is Temporal Prompting All We Need For Limited Labeled Action Recognition?**|Shreyank N Gowda et.al.|[2504.01890v1](http://arxiv.org/abs/2504.01890v1)|null|

|**2025-04-02**|**GMAI-VL-R1: Harnessing Reinforcement Learning for Multimodal Medical Reasoning**|Yanzhou Su et.al.|[2504.01886v1](http://arxiv.org/abs/2504.01886v1)|null|

|**2025-04-02**|**CoRAG: Collaborative Retrieval-Augmented Generation**|Aashiq Muhamed et.al.|[2504.01883v1](http://arxiv.org/abs/2504.01883v1)|null|

|**2025-04-02**|**CO-DEFEND: Continuous Decentralized Federated Learning for Secure DoH-Based Threat Detection**|Diego Cajaraville-Aboy et.al.|[2504.01882v1](http://arxiv.org/abs/2504.01882v1)|null|

|**2025-04-02**|**Architect Your Landscape Approach (AYLA) for Optimizations in Deep Learning**|Ben Keslaki et.al.|[2504.01875v1](http://arxiv.org/abs/2504.01875v1)|null|

|**2025-04-02**|**Interpreting Emergent Planning in Model-Free Reinforcement Learning**|Thomas Bush et.al.|[2504.01871v1](http://arxiv.org/abs/2504.01871v1)|null|

|**2025-04-02**|**Buggin: Automatic intrinsic bugs classification model using NLP and ML**|Pragya Bhandari et.al.|[2504.01869v1](http://arxiv.org/abs/2504.01869v1)|null|

### Efficient

|Publish Date|Title|Authors|PDF|Code|

| :---: | :---: | :---: | :---: | :---: |

|**2025-04-02**|**Efficient Federated Learning Tiny Language Models for Mobile Network Feature Prediction**|Daniel Becking et.al.|[2504.01947v1](http://arxiv.org/abs/2504.01947v1)|null|

|**2025-04-02**|**Client Selection in Federated Learning with Data Heterogeneity and Network Latencies**|Harsh Vardhan et.al.|[2504.01921v1](http://arxiv.org/abs/2504.01921v1)|null|

|**2025-04-02**|**CO-DEFEND: Continuous Decentralized Federated Learning for Secure DoH-Based Threat Detection**|Diego Cajaraville-Aboy et.al.|[2504.01882v1](http://arxiv.org/abs/2504.01882v1)|null|

|**2025-04-02**|**A Randomized Zeroth-Order Hierarchical Framework for Heterogeneous Federated Learning**|Yuyang Qiu et.al.|[2504.01839v1](http://arxiv.org/abs/2504.01839v1)|null|

|**2025-04-02**|**A Two-Timescale Approach for Wireless Federated Learning with Parameter Freezing and Power Control**|Jinhao Ouyang et.al.|[2504.01752v1](http://arxiv.org/abs/2504.01752v1)|null|

|**2025-04-02**|**Sky of Unlearning (SoUL): Rewiring Federated Machine Unlearning via Selective Pruning**|Md Mahabub Uz Zaman et.al.|[2504.01705v1](http://arxiv.org/abs/2504.01705v1)|null|

|**2025-04-02**|**Satellite Edge Artificial Intelligence with Large Models: Architectures and Technologies**|Yuanming Shi et.al.|[2504.01676v1](http://arxiv.org/abs/2504.01676v1)|null|

|**2025-04-02**|**Accelerating the discovery of high-performance nonlinear optical materials using active learning and high-throughput screening**|Victor Trinquet et.al.|[2504.01526v1](http://arxiv.org/abs/2504.01526v1)|null|

|**2025-04-02**|**Split Federated Learning for UAV-Enabled Integrated Sensing, Computation, and Communication**|Xiangwang Hou et.al.|[2504.01443v1](http://arxiv.org/abs/2504.01443v1)|null|

|**2025-04-02**|**Age-Aware Partial Gradient Update Strategy for Federated Learning Over the Air**|Ruihao Du et.al.|[2504.01357v1](http://arxiv.org/abs/2504.01357v1)|null|

|**2025-04-01**|**Towards Resilient Federated Learning in CyberEdge Networks: Recent Advances and Future Trends**|Kai Li et.al.|[2504.01240v1](http://arxiv.org/abs/2504.01240v1)|null|

|**2025-04-01**|**Personalized Federated Training of Diffusion Models with Privacy Guarantees**|Kumar Kshitij Patel et.al.|[2504.00952v1](http://arxiv.org/abs/2504.00952v1)|null|

|**2025-04-01**|**Benchmarking Federated Machine Unlearning methods for Tabular Data**|Chenguang Xiao et.al.|[2504.00921v1](http://arxiv.org/abs/2504.00921v1)|null|

|**2025-04-01**|**Exploring Personalized Federated Learning Architectures for Violence Detection in Surveillance Videos**|Mohammad Kassir et.al.|[2504.00857v1](http://arxiv.org/abs/2504.00857v1)|null|

|**2025-04-01**|**Global Intervention and Distillation for Federated Out-of-Distribution Generalization**|Zhuang Qi et.al.|[2504.00850v1](http://arxiv.org/abs/2504.00850v1)|null|

|**2025-04-01**|**Optimizing Resource Allocation and Energy Efficiency in Federated Fog Computing for IoT**|Syed Sarmad Shah et.al.|[2504.00791v1](http://arxiv.org/abs/2504.00791v1)|null|

|**2025-04-01**|**EMO: Edge Model Overlays to Scale Model Size in Federated Learning**|Di Wu et.al.|[2504.00726v1](http://arxiv.org/abs/2504.00726v1)|null|

|**2025-04-01**|**Adaptive Federated Learning with Functional Encryption: A Comparison of Classical and Quantum-safe Options**|Enrico Sorbera et.al.|[2504.00563v1](http://arxiv.org/abs/2504.00563v1)|null|

|**2025-04-01**|**Informed Greedy Algorithm for Scalable Bayesian Network Fusion via Minimum Cut Analysis**|Pablo Torrijos et.al.|[2504.00467v1](http://arxiv.org/abs/2504.00467v1)|null|

|**2025-04-01**|**FedPaI: Achieving Extreme Sparsity in Federated Learning via Pruning at Initialization**|Haonan Wang et.al.|[2504.00308v1](http://arxiv.org/abs/2504.00308v1)|null|

|**2025-03-31**|**Federated Learning for Cross-Domain Data Privacy: A Distributed Approach to Secure Collaboration**|Yiwei Zhang et.al.|[2504.00282v1](http://arxiv.org/abs/2504.00282v1)|null|

|**2025-03-31**|**RailGoerl24: Görlitz Rail Test Center CV Dataset 2024**|Rustam Tagiew et.al.|[2504.00204v1](http://arxiv.org/abs/2504.00204v1)|null|

|**2025-03-31**|**Few-Shot Generation of Brain Tumors for Secure and Fair Data Sharing**|Yongyi Shi et.al.|[2504.00150v1](http://arxiv.org/abs/2504.00150v1)|null|

|**2025-03-31**|**Navigating Decentralized Online Social Networks: An Overview of Technical and Societal Challenges in Architectural Choices**|Ujun Jeong et.al.|[2504.00071v1](http://arxiv.org/abs/2504.00071v1)|null|

|**2025-03-31**|**Federated Structured Sparse PCA for Anomaly Detection in IoT Networks**|Chenyi Huang et.al.|[2503.23981v1](http://arxiv.org/abs/2503.23981v1)|null|

|**2025-03-31**|**Communication-Efficient and Personalized Federated Foundation Model Fine-Tuning via Tri-Matrix Adaptation**|Yongle Li et.al.|[2503.23869v1](http://arxiv.org/abs/2503.23869v1)|null|

|**2025-03-31**|**Blockchain for Federated Learning in the Internet of Things: Trustworthy Adaptation, Standards, and the Road Ahead**|Farhana Javed et.al.|[2503.23823v1](http://arxiv.org/abs/2503.23823v1)|null|

|**2025-03-30**|**Buffer is All You Need: Defending Federated Learning against Backdoor Attacks under Non-iids via Buffering**|Xingyu Lyu et.al.|[2503.23511v1](http://arxiv.org/abs/2503.23511v1)|null|

|**2025-03-30**|**Federated Self-Supervised Learning for One-Shot Cross-Modal and Cross-Imaging Technique Segmentation**|Siladittya Manna et.al.|[2503.23507v1](http://arxiv.org/abs/2503.23507v1)|null|

|**2025-03-30**|**A Systematic Decade Review of Trip Route Planning with Travel Time Estimation based on User Preferences and Behavior**|Nikil Jayasuriya et.al.|[2503.23486v1](http://arxiv.org/abs/2503.23486v1)|null|

### Asynchronous

|Publish Date|Title|Authors|PDF|Code|

| :---: | :---: | :---: | :---: | :---: |

|**2025-04-02**|**Efficient Federated Learning Tiny Language Models for Mobile Network Feature Prediction**|Daniel Becking et.al.|[2504.01947v1](http://arxiv.org/abs/2504.01947v1)|null|

|**2025-04-02**|**Client Selection in Federated Learning with Data Heterogeneity and Network Latencies**|Harsh Vardhan et.al.|[2504.01921v1](http://arxiv.org/abs/2504.01921v1)|null|

|**2025-04-02**|**CO-DEFEND: Continuous Decentralized Federated Learning for Secure DoH-Based Threat Detection**|Diego Cajaraville-Aboy et.al.|[2504.01882v1](http://arxiv.org/abs/2504.01882v1)|null|

|**2025-04-02**|**A Randomized Zeroth-Order Hierarchical Framework for Heterogeneous Federated Learning**|Yuyang Qiu et.al.|[2504.01839v1](http://arxiv.org/abs/2504.01839v1)|null|

|**2025-04-02**|**A Two-Timescale Approach for Wireless Federated Learning with Parameter Freezing and Power Control**|Jinhao Ouyang et.al.|[2504.01752v1](http://arxiv.org/abs/2504.01752v1)|null|

|**2025-04-02**|**Sky of Unlearning (SoUL): Rewiring Federated Machine Unlearning via Selective Pruning**|Md Mahabub Uz Zaman et.al.|[2504.01705v1](http://arxiv.org/abs/2504.01705v1)|null|

|**2025-04-02**|**Satellite Edge Artificial Intelligence with Large Models: Architectures and Technologies**|Yuanming Shi et.al.|[2504.01676v1](http://arxiv.org/abs/2504.01676v1)|null|

|**2025-04-02**|**Accelerating the discovery of high-performance nonlinear optical materials using active learning and high-throughput screening**|Victor Trinquet et.al.|[2504.01526v1](http://arxiv.org/abs/2504.01526v1)|null|

|**2025-04-02**|**Split Federated Learning for UAV-Enabled Integrated Sensing, Computation, and Communication**|Xiangwang Hou et.al.|[2504.01443v1](http://arxiv.org/abs/2504.01443v1)|null|

|**2025-04-02**|**Age-Aware Partial Gradient Update Strategy for Federated Learning Over the Air**|Ruihao Du et.al.|[2504.01357v1](http://arxiv.org/abs/2504.01357v1)|null|

|**2025-04-01**|**Towards Resilient Federated Learning in CyberEdge Networks: Recent Advances and Future Trends**|Kai Li et.al.|[2504.01240v1](http://arxiv.org/abs/2504.01240v1)|null|

|**2025-04-01**|**Personalized Federated Training of Diffusion Models with Privacy Guarantees**|Kumar Kshitij Patel et.al.|[2504.00952v1](http://arxiv.org/abs/2504.00952v1)|null|

|**2025-04-01**|**Benchmarking Federated Machine Unlearning methods for Tabular Data**|Chenguang Xiao et.al.|[2504.00921v1](http://arxiv.org/abs/2504.00921v1)|null|

|**2025-04-01**|**Exploring Personalized Federated Learning Architectures for Violence Detection in Surveillance Videos**|Mohammad Kassir et.al.|[2504.00857v1](http://arxiv.org/abs/2504.00857v1)|null|

|**2025-04-01**|**Global Intervention and Distillation for Federated Out-of-Distribution Generalization**|Zhuang Qi et.al.|[2504.00850v1](http://arxiv.org/abs/2504.00850v1)|null|

|**2025-04-01**|**Optimizing Resource Allocation and Energy Efficiency in Federated Fog Computing for IoT**|Syed Sarmad Shah et.al.|[2504.00791v1](http://arxiv.org/abs/2504.00791v1)|null|

|**2025-04-01**|**EMO: Edge Model Overlays to Scale Model Size in Federated Learning**|Di Wu et.al.|[2504.00726v1](http://arxiv.org/abs/2504.00726v1)|null|

|**2025-04-01**|**Adaptive Federated Learning with Functional Encryption: A Comparison of Classical and Quantum-safe Options**|Enrico Sorbera et.al.|[2504.00563v1](http://arxiv.org/abs/2504.00563v1)|null|

|**2025-04-01**|**Informed Greedy Algorithm for Scalable Bayesian Network Fusion via Minimum Cut Analysis**|Pablo Torrijos et.al.|[2504.00467v1](http://arxiv.org/abs/2504.00467v1)|null|

|**2025-04-01**|**FedPaI: Achieving Extreme Sparsity in Federated Learning via Pruning at Initialization**|Haonan Wang et.al.|[2504.00308v1](http://arxiv.org/abs/2504.00308v1)|null|

|**2025-03-31**|**Federated Learning for Cross-Domain Data Privacy: A Distributed Approach to Secure Collaboration**|Yiwei Zhang et.al.|[2504.00282v1](http://arxiv.org/abs/2504.00282v1)|null|

|**2025-03-31**|**RailGoerl24: Görlitz Rail Test Center CV Dataset 2024**|Rustam Tagiew et.al.|[2504.00204v1](http://arxiv.org/abs/2504.00204v1)|null|

|**2025-03-31**|**Few-Shot Generation of Brain Tumors for Secure and Fair Data Sharing**|Yongyi Shi et.al.|[2504.00150v1](http://arxiv.org/abs/2504.00150v1)|null|

|**2025-03-31**|**Navigating Decentralized Online Social Networks: An Overview of Technical and Societal Challenges in Architectural Choices**|Ujun Jeong et.al.|[2504.00071v1](http://arxiv.org/abs/2504.00071v1)|null|

|**2025-03-31**|**Federated Structured Sparse PCA for Anomaly Detection in IoT Networks**|Chenyi Huang et.al.|[2503.23981v1](http://arxiv.org/abs/2503.23981v1)|null|

|**2025-03-31**|**Communication-Efficient and Personalized Federated Foundation Model Fine-Tuning via Tri-Matrix Adaptation**|Yongle Li et.al.|[2503.23869v1](http://arxiv.org/abs/2503.23869v1)|null|

|**2025-03-31**|**Blockchain for Federated Learning in the Internet of Things: Trustworthy Adaptation, Standards, and the Road Ahead**|Farhana Javed et.al.|[2503.23823v1](http://arxiv.org/abs/2503.23823v1)|null|

|**2025-03-30**|**Buffer is All You Need: Defending Federated Learning against Backdoor Attacks under Non-iids via Buffering**|Xingyu Lyu et.al.|[2503.23511v1](http://arxiv.org/abs/2503.23511v1)|null|

|**2025-03-30**|**Federated Self-Supervised Learning for One-Shot Cross-Modal and Cross-Imaging Technique Segmentation**|Siladittya Manna et.al.|[2503.23507v1](http://arxiv.org/abs/2503.23507v1)|null|

|**2025-03-30**|**A Systematic Decade Review of Trip Route Planning with Travel Time Estimation based on User Preferences and Behavior**|Nikil Jayasuriya et.al.|[2503.23486v1](http://arxiv.org/abs/2503.23486v1)|null|

### Privacy

|Publish Date|Title|Authors|PDF|Code|

| :---: | :---: | :---: | :---: | :---: |

|**2025-04-02**|**Efficient Federated Learning Tiny Language Models for Mobile Network Feature Prediction**|Daniel Becking et.al.|[2504.01947v1](http://arxiv.org/abs/2504.01947v1)|null|

|**2025-04-02**|**Client Selection in Federated Learning with Data Heterogeneity and Network Latencies**|Harsh Vardhan et.al.|[2504.01921v1](http://arxiv.org/abs/2504.01921v1)|null|

|**2025-04-02**|**CO-DEFEND: Continuous Decentralized Federated Learning for Secure DoH-Based Threat Detection**|Diego Cajaraville-Aboy et.al.|[2504.01882v1](http://arxiv.org/abs/2504.01882v1)|null|

|**2025-04-02**|**A Randomized Zeroth-Order Hierarchical Framework for Heterogeneous Federated Learning**|Yuyang Qiu et.al.|[2504.01839v1](http://arxiv.org/abs/2504.01839v1)|null|

|**2025-04-02**|**A Two-Timescale Approach for Wireless Federated Learning with Parameter Freezing and Power Control**|Jinhao Ouyang et.al.|[2504.01752v1](http://arxiv.org/abs/2504.01752v1)|null|

|**2025-04-02**|**Sky of Unlearning (SoUL): Rewiring Federated Machine Unlearning via Selective Pruning**|Md Mahabub Uz Zaman et.al.|[2504.01705v1](http://arxiv.org/abs/2504.01705v1)|null|

|**2025-04-02**|**Satellite Edge Artificial Intelligence with Large Models: Architectures and Technologies**|Yuanming Shi et.al.|[2504.01676v1](http://arxiv.org/abs/2504.01676v1)|null|

|**2025-04-02**|**Accelerating the discovery of high-performance nonlinear optical materials using active learning and high-throughput screening**|Victor Trinquet et.al.|[2504.01526v1](http://arxiv.org/abs/2504.01526v1)|null|

|**2025-04-02**|**Split Federated Learning for UAV-Enabled Integrated Sensing, Computation, and Communication**|Xiangwang Hou et.al.|[2504.01443v1](http://arxiv.org/abs/2504.01443v1)|null|

|**2025-04-02**|**Age-Aware Partial Gradient Update Strategy for Federated Learning Over the Air**|Ruihao Du et.al.|[2504.01357v1](http://arxiv.org/abs/2504.01357v1)|null|

|**2025-04-01**|**Towards Resilient Federated Learning in CyberEdge Networks: Recent Advances and Future Trends**|Kai Li et.al.|[2504.01240v1](http://arxiv.org/abs/2504.01240v1)|null|

|**2025-04-01**|**Personalized Federated Training of Diffusion Models with Privacy Guarantees**|Kumar Kshitij Patel et.al.|[2504.00952v1](http://arxiv.org/abs/2504.00952v1)|null|

|**2025-04-01**|**Benchmarking Federated Machine Unlearning methods for Tabular Data**|Chenguang Xiao et.al.|[2504.00921v1](http://arxiv.org/abs/2504.00921v1)|null|

|**2025-04-01**|**Exploring Personalized Federated Learning Architectures for Violence Detection in Surveillance Videos**|Mohammad Kassir et.al.|[2504.00857v1](http://arxiv.org/abs/2504.00857v1)|null|

|**2025-04-01**|**Global Intervention and Distillation for Federated Out-of-Distribution Generalization**|Zhuang Qi et.al.|[2504.00850v1](http://arxiv.org/abs/2504.00850v1)|null|

|**2025-04-01**|**Optimizing Resource Allocation and Energy Efficiency in Federated Fog Computing for IoT**|Syed Sarmad Shah et.al.|[2504.00791v1](http://arxiv.org/abs/2504.00791v1)|null|

|**2025-04-01**|**EMO: Edge Model Overlays to Scale Model Size in Federated Learning**|Di Wu et.al.|[2504.00726v1](http://arxiv.org/abs/2504.00726v1)|null|

|**2025-04-01**|**Adaptive Federated Learning with Functional Encryption: A Comparison of Classical and Quantum-safe Options**|Enrico Sorbera et.al.|[2504.00563v1](http://arxiv.org/abs/2504.00563v1)|null|

|**2025-04-01**|**Informed Greedy Algorithm for Scalable Bayesian Network Fusion via Minimum Cut Analysis**|Pablo Torrijos et.al.|[2504.00467v1](http://arxiv.org/abs/2504.00467v1)|null|

|**2025-04-01**|**FedPaI: Achieving Extreme Sparsity in Federated Learning via Pruning at Initialization**|Haonan Wang et.al.|[2504.00308v1](http://arxiv.org/abs/2504.00308v1)|null|

|**2025-03-31**|**Federated Learning for Cross-Domain Data Privacy: A Distributed Approach to Secure Collaboration**|Yiwei Zhang et.al.|[2504.00282v1](http://arxiv.org/abs/2504.00282v1)|null|

|**2025-03-31**|**RailGoerl24: Görlitz Rail Test Center CV Dataset 2024**|Rustam Tagiew et.al.|[2504.00204v1](http://arxiv.org/abs/2504.00204v1)|null|

|**2025-03-31**|**Few-Shot Generation of Brain Tumors for Secure and Fair Data Sharing**|Yongyi Shi et.al.|[2504.00150v1](http://arxiv.org/abs/2504.00150v1)|null|

|**2025-03-31**|**Navigating Decentralized Online Social Networks: An Overview of Technical and Societal Challenges in Architectural Choices**|Ujun Jeong et.al.|[2504.00071v1](http://arxiv.org/abs/2504.00071v1)|null|

|**2025-03-31**|**Federated Structured Sparse PCA for Anomaly Detection in IoT Networks**|Chenyi Huang et.al.|[2503.23981v1](http://arxiv.org/abs/2503.23981v1)|null|

|**2025-03-31**|**Communication-Efficient and Personalized Federated Foundation Model Fine-Tuning via Tri-Matrix Adaptation**|Yongle Li et.al.|[2503.23869v1](http://arxiv.org/abs/2503.23869v1)|null|

|**2025-03-31**|**Blockchain for Federated Learning in the Internet of Things: Trustworthy Adaptation, Standards, and the Road Ahead**|Farhana Javed et.al.|[2503.23823v1](http://arxiv.org/abs/2503.23823v1)|null|

|**2025-03-30**|**Buffer is All You Need: Defending Federated Learning against Backdoor Attacks under Non-iids via Buffering**|Xingyu Lyu et.al.|[2503.23511v1](http://arxiv.org/abs/2503.23511v1)|null|

|**2025-03-30**|**Federated Self-Supervised Learning for One-Shot Cross-Modal and Cross-Imaging Technique Segmentation**|Siladittya Manna et.al.|[2503.23507v1](http://arxiv.org/abs/2503.23507v1)|null|

|**2025-03-30**|**A Systematic Decade Review of Trip Route Planning with Travel Time Estimation based on User Preferences and Behavior**|Nikil Jayasuriya et.al.|[2503.23486v1](http://arxiv.org/abs/2503.23486v1)|null|

### Personalized

|Publish Date|Title|Authors|PDF|Code|

| :---: | :---: | :---: | :---: | :---: |

|**2025-04-02**|**Deep Representation Learning for Unsupervised Clustering of Myocardial Fiber Trajectories in Cardiac Diffusion Tensor Imaging**|Mohini Anand et.al.|[2504.01953v1](http://arxiv.org/abs/2504.01953v1)|null|

|**2025-04-02**|**Efficient Federated Learning Tiny Language Models for Mobile Network Feature Prediction**|Daniel Becking et.al.|[2504.01947v1](http://arxiv.org/abs/2504.01947v1)|null|

|**2025-04-02**|**Client Selection in Federated Learning with Data Heterogeneity and Network Latencies**|Harsh Vardhan et.al.|[2504.01921v1](http://arxiv.org/abs/2504.01921v1)|null|

|**2025-04-02**|**Dual mechanism of Anti-Seizure Medications in controlling seizure activity**|Guillermo M. Besne et.al.|[2504.01887v1](http://arxiv.org/abs/2504.01887v1)|null|

|**2025-04-02**|**CO-DEFEND: Continuous Decentralized Federated Learning for Secure DoH-Based Threat Detection**|Diego Cajaraville-Aboy et.al.|[2504.01882v1](http://arxiv.org/abs/2504.01882v1)|null|

|**2025-04-02**|**Extending MovieLens-32M to Provide New Evaluation Objectives**|Mark D. Smucker et.al.|[2504.01863v1](http://arxiv.org/abs/2504.01863v1)|null|

|**2025-04-02**|**A Randomized Zeroth-Order Hierarchical Framework for Heterogeneous Federated Learning**|Yuyang Qiu et.al.|[2504.01839v1](http://arxiv.org/abs/2504.01839v1)|null|

|**2025-04-02**|**The Factors Influencing Well-Being in Software Engineers: A Cross-Country Mixed-Method Study**|Cristina Martinez Montes et.al.|[2504.01787v1](http://arxiv.org/abs/2504.01787v1)|null|

|**2025-04-02**|**Leveraging Embedding Techniques in Multimodal Machine Learning for Mental Illness Assessment**|Abdelrahaman A. Hassan et.al.|[2504.01767v1](http://arxiv.org/abs/2504.01767v1)|null|

|**2025-04-02**|**A Two-Timescale Approach for Wireless Federated Learning with Parameter Freezing and Power Control**|Jinhao Ouyang et.al.|[2504.01752v1](http://arxiv.org/abs/2504.01752v1)|null|

|**2025-04-02**|**Sky of Unlearning (SoUL): Rewiring Federated Machine Unlearning via Selective Pruning**|Md Mahabub Uz Zaman et.al.|[2504.01705v1](http://arxiv.org/abs/2504.01705v1)|null|

|**2025-04-02**|**Reasoning LLMs for User-Aware Multimodal Conversational Agents**|Hamed Rahimi et.al.|[2504.01700v1](http://arxiv.org/abs/2504.01700v1)|null|

|**2025-04-02**|**Satellite Edge Artificial Intelligence with Large Models: Architectures and Technologies**|Yuanming Shi et.al.|[2504.01676v1](http://arxiv.org/abs/2504.01676v1)|null|

|**2025-04-02**|**Automatic Estimation of Pedestrian Gait Features using a single camera recording: Algorithm and Statistical Analysis for Gender Difference and Obstacle Interactions**|Kanika Jain et.al.|[2504.01600v1](http://arxiv.org/abs/2504.01600v1)|null|

|**2025-04-02**|**Building Knowledge from Interactions: An LLM-Based Architecture for Adaptive Tutoring and Social Reasoning**|Luca Garello et.al.|[2504.01588v1](http://arxiv.org/abs/2504.01588v1)|null|

|**2025-04-02**|**Predicting passenger injury distributions under uncertainty variables using Gaussian process modeling with GHBMC**|Changmin Baek et.al.|[2504.01530v2](http://arxiv.org/abs/2504.01530v2)|null|

|**2025-04-02**|**Accelerating the discovery of high-performance nonlinear optical materials using active learning and high-throughput screening**|Victor Trinquet et.al.|[2504.01526v1](http://arxiv.org/abs/2504.01526v1)|null|

|**2025-04-02**|**Domain Guidance: A Simple Transfer Approach for a Pre-trained Diffusion Model**|Jincheng Zhong et.al.|[2504.01521v1](http://arxiv.org/abs/2504.01521v1)|null|

|**2025-04-02**|**Detecting Lip-Syncing Deepfakes: Vision Temporal Transformer for Analyzing Mouth Inconsistencies**|Soumyya Kanti Datta et.al.|[2504.01470v1](http://arxiv.org/abs/2504.01470v1)|null|

|**2025-04-02**|**Split Federated Learning for UAV-Enabled Integrated Sensing, Computation, and Communication**|Xiangwang Hou et.al.|[2504.01443v1](http://arxiv.org/abs/2504.01443v1)|null|

|**2025-04-02**|**Age-Aware Partial Gradient Update Strategy for Federated Learning Over the Air**|Ruihao Du et.al.|[2504.01357v1](http://arxiv.org/abs/2504.01357v1)|null|

|**2025-04-02**|**Intuitive Human-Drone Collaborative Navigation in Unknown Environments through Mixed Reality**|Sanket A. Salunkhe et.al.|[2504.01350v1](http://arxiv.org/abs/2504.01350v1)|null|

|**2025-04-01**|**Grade Guard: A Smart System for Short Answer Automated Grading**|Niharika Dadu et.al.|[2504.01253v1](http://arxiv.org/abs/2504.01253v1)|null|

|**2025-04-01**|**Towards Resilient Federated Learning in CyberEdge Networks: Recent Advances and Future Trends**|Kai Li et.al.|[2504.01240v1](http://arxiv.org/abs/2504.01240v1)|null|

|**2025-04-01**|**Evaluating Electric Micro-Mobility Related Mode Choice Stated Preferences: A Latent Class Choice Approach**|Yikang Wu et.al.|[2504.01237v1](http://arxiv.org/abs/2504.01237v1)|null|

|**2025-04-01**|**Epistemic Alignment: A Mediating Framework for User-LLM Knowledge Delivery**|Nicholas Clark et.al.|[2504.01205v1](http://arxiv.org/abs/2504.01205v1)|null|

|**2025-04-01**|**Reminiscences about Steven Weinberg (This Time it's Personal)**|C. P. Burgess et.al.|[2504.01118v1](http://arxiv.org/abs/2504.01118v1)|null|

|**2025-04-01**|**MixerMDM: Learnable Composition of Human Motion Diffusion Models**|Pablo Ruiz-Ponce et.al.|[2504.01019v1](http://arxiv.org/abs/2504.01019v1)|null|

|**2025-04-01**|**Open, Small, Rigmarole -- Evaluating Llama 3.2 3B's Feedback for Programming Exercises**|Imen Azaiz et.al.|[2504.01054v1](http://arxiv.org/abs/2504.01054v1)|null|

|**2025-04-01**|**IDMR: Towards Instance-Driven Precise Visual Correspondence in Multimodal Retrieval**|Bangwei Liu et.al.|[2504.00954v1](http://arxiv.org/abs/2504.00954v1)|null|

### Communication

|Publish Date|Title|Authors|PDF|Code|

| :---: | :---: | :---: | :---: | :---: |

|**2025-04-02**|**Efficient Federated Learning Tiny Language Models for Mobile Network Feature Prediction**|Daniel Becking et.al.|[2504.01947v1](http://arxiv.org/abs/2504.01947v1)|null|

|**2025-04-02**|**Client Selection in Federated Learning with Data Heterogeneity and Network Latencies**|Harsh Vardhan et.al.|[2504.01921v1](http://arxiv.org/abs/2504.01921v1)|null|

|**2025-04-02**|**CO-DEFEND: Continuous Decentralized Federated Learning for Secure DoH-Based Threat Detection**|Diego Cajaraville-Aboy et.al.|[2504.01882v1](http://arxiv.org/abs/2504.01882v1)|null|

|**2025-04-02**|**A Randomized Zeroth-Order Hierarchical Framework for Heterogeneous Federated Learning**|Yuyang Qiu et.al.|[2504.01839v1](http://arxiv.org/abs/2504.01839v1)|null|

|**2025-04-02**|**A Two-Timescale Approach for Wireless Federated Learning with Parameter Freezing and Power Control**|Jinhao Ouyang et.al.|[2504.01752v1](http://arxiv.org/abs/2504.01752v1)|null|

|**2025-04-02**|**Sky of Unlearning (SoUL): Rewiring Federated Machine Unlearning via Selective Pruning**|Md Mahabub Uz Zaman et.al.|[2504.01705v1](http://arxiv.org/abs/2504.01705v1)|null|

|**2025-04-02**|**Satellite Edge Artificial Intelligence with Large Models: Architectures and Technologies**|Yuanming Shi et.al.|[2504.01676v1](http://arxiv.org/abs/2504.01676v1)|null|

|**2025-04-02**|**Accelerating the discovery of high-performance nonlinear optical materials using active learning and high-throughput screening**|Victor Trinquet et.al.|[2504.01526v1](http://arxiv.org/abs/2504.01526v1)|null|

|**2025-04-02**|**Split Federated Learning for UAV-Enabled Integrated Sensing, Computation, and Communication**|Xiangwang Hou et.al.|[2504.01443v1](http://arxiv.org/abs/2504.01443v1)|null|

|**2025-04-02**|**Age-Aware Partial Gradient Update Strategy for Federated Learning Over the Air**|Ruihao Du et.al.|[2504.01357v1](http://arxiv.org/abs/2504.01357v1)|null|

|**2025-04-01**|**Towards Resilient Federated Learning in CyberEdge Networks: Recent Advances and Future Trends**|Kai Li et.al.|[2504.01240v1](http://arxiv.org/abs/2504.01240v1)|null|

|**2025-04-01**|**Personalized Federated Training of Diffusion Models with Privacy Guarantees**|Kumar Kshitij Patel et.al.|[2504.00952v1](http://arxiv.org/abs/2504.00952v1)|null|

|**2025-04-01**|**Benchmarking Federated Machine Unlearning methods for Tabular Data**|Chenguang Xiao et.al.|[2504.00921v1](http://arxiv.org/abs/2504.00921v1)|null|

|**2025-04-01**|**Exploring Personalized Federated Learning Architectures for Violence Detection in Surveillance Videos**|Mohammad Kassir et.al.|[2504.00857v1](http://arxiv.org/abs/2504.00857v1)|null|

|**2025-04-01**|**Global Intervention and Distillation for Federated Out-of-Distribution Generalization**|Zhuang Qi et.al.|[2504.00850v1](http://arxiv.org/abs/2504.00850v1)|null|

|**2025-04-01**|**Optimizing Resource Allocation and Energy Efficiency in Federated Fog Computing for IoT**|Syed Sarmad Shah et.al.|[2504.00791v1](http://arxiv.org/abs/2504.00791v1)|null|

|**2025-04-01**|**EMO: Edge Model Overlays to Scale Model Size in Federated Learning**|Di Wu et.al.|[2504.00726v1](http://arxiv.org/abs/2504.00726v1)|null|

|**2025-04-01**|**Adaptive Federated Learning with Functional Encryption: A Comparison of Classical and Quantum-safe Options**|Enrico Sorbera et.al.|[2504.00563v1](http://arxiv.org/abs/2504.00563v1)|null|

|**2025-04-01**|**Informed Greedy Algorithm for Scalable Bayesian Network Fusion via Minimum Cut Analysis**|Pablo Torrijos et.al.|[2504.00467v1](http://arxiv.org/abs/2504.00467v1)|null|

|**2025-04-01**|**FedPaI: Achieving Extreme Sparsity in Federated Learning via Pruning at Initialization**|Haonan Wang et.al.|[2504.00308v1](http://arxiv.org/abs/2504.00308v1)|null|

|**2025-03-31**|**Federated Learning for Cross-Domain Data Privacy: A Distributed Approach to Secure Collaboration**|Yiwei Zhang et.al.|[2504.00282v1](http://arxiv.org/abs/2504.00282v1)|null|

|**2025-03-31**|**RailGoerl24: Görlitz Rail Test Center CV Dataset 2024**|Rustam Tagiew et.al.|[2504.00204v1](http://arxiv.org/abs/2504.00204v1)|null|

|**2025-03-31**|**Few-Shot Generation of Brain Tumors for Secure and Fair Data Sharing**|Yongyi Shi et.al.|[2504.00150v1](http://arxiv.org/abs/2504.00150v1)|null|

|**2025-03-31**|**Navigating Decentralized Online Social Networks: An Overview of Technical and Societal Challenges in Architectural Choices**|Ujun Jeong et.al.|[2504.00071v1](http://arxiv.org/abs/2504.00071v1)|null|

|**2025-03-31**|**Federated Structured Sparse PCA for Anomaly Detection in IoT Networks**|Chenyi Huang et.al.|[2503.23981v1](http://arxiv.org/abs/2503.23981v1)|null|

|**2025-03-31**|**Communication-Efficient and Personalized Federated Foundation Model Fine-Tuning via Tri-Matrix Adaptation**|Yongle Li et.al.|[2503.23869v1](http://arxiv.org/abs/2503.23869v1)|null|

|**2025-03-31**|**Blockchain for Federated Learning in the Internet of Things: Trustworthy Adaptation, Standards, and the Road Ahead**|Farhana Javed et.al.|[2503.23823v1](http://arxiv.org/abs/2503.23823v1)|null|

|**2025-03-30**|**Buffer is All You Need: Defending Federated Learning against Backdoor Attacks under Non-iids via Buffering**|Xingyu Lyu et.al.|[2503.23511v1](http://arxiv.org/abs/2503.23511v1)|null|

|**2025-03-30**|**Federated Self-Supervised Learning for One-Shot Cross-Modal and Cross-Imaging Technique Segmentation**|Siladittya Manna et.al.|[2503.23507v1](http://arxiv.org/abs/2503.23507v1)|null|

|**2025-03-30**|**A Systematic Decade Review of Trip Route Planning with Travel Time Estimation based on User Preferences and Behavior**|Nikil Jayasuriya et.al.|[2503.23486v1](http://arxiv.org/abs/2503.23486v1)|null|

### Heterogeneous

|Publish Date|Title|Authors|PDF|Code|

| :---: | :---: | :---: | :---: | :---: |

|**2025-04-02**|**Efficient Federated Learning Tiny Language Models for Mobile Network Feature Prediction**|Daniel Becking et.al.|[2504.01947v1](http://arxiv.org/abs/2504.01947v1)|null|

|**2025-04-02**|**Client Selection in Federated Learning with Data Heterogeneity and Network Latencies**|Harsh Vardhan et.al.|[2504.01921v1](http://arxiv.org/abs/2504.01921v1)|null|

|**2025-04-02**|**CO-DEFEND: Continuous Decentralized Federated Learning for Secure DoH-Based Threat Detection**|Diego Cajaraville-Aboy et.al.|[2504.01882v1](http://arxiv.org/abs/2504.01882v1)|null|

|**2025-04-02**|**A Randomized Zeroth-Order Hierarchical Framework for Heterogeneous Federated Learning**|Yuyang Qiu et.al.|[2504.01839v1](http://arxiv.org/abs/2504.01839v1)|null|

|**2025-04-02**|**A Two-Timescale Approach for Wireless Federated Learning with Parameter Freezing and Power Control**|Jinhao Ouyang et.al.|[2504.01752v1](http://arxiv.org/abs/2504.01752v1)|null|

|**2025-04-02**|**Sky of Unlearning (SoUL): Rewiring Federated Machine Unlearning via Selective Pruning**|Md Mahabub Uz Zaman et.al.|[2504.01705v1](http://arxiv.org/abs/2504.01705v1)|null|

|**2025-04-02**|**Satellite Edge Artificial Intelligence with Large Models: Architectures and Technologies**|Yuanming Shi et.al.|[2504.01676v1](http://arxiv.org/abs/2504.01676v1)|null|

|**2025-04-02**|**Accelerating the discovery of high-performance nonlinear optical materials using active learning and high-throughput screening**|Victor Trinquet et.al.|[2504.01526v1](http://arxiv.org/abs/2504.01526v1)|null|

|**2025-04-02**|**Split Federated Learning for UAV-Enabled Integrated Sensing, Computation, and Communication**|Xiangwang Hou et.al.|[2504.01443v1](http://arxiv.org/abs/2504.01443v1)|null|

|**2025-04-02**|**Age-Aware Partial Gradient Update Strategy for Federated Learning Over the Air**|Ruihao Du et.al.|[2504.01357v1](http://arxiv.org/abs/2504.01357v1)|null|

|**2025-04-01**|**Towards Resilient Federated Learning in CyberEdge Networks: Recent Advances and Future Trends**|Kai Li et.al.|[2504.01240v1](http://arxiv.org/abs/2504.01240v1)|null|

|**2025-04-01**|**Personalized Federated Training of Diffusion Models with Privacy Guarantees**|Kumar Kshitij Patel et.al.|[2504.00952v1](http://arxiv.org/abs/2504.00952v1)|null|

|**2025-04-01**|**Benchmarking Federated Machine Unlearning methods for Tabular Data**|Chenguang Xiao et.al.|[2504.00921v1](http://arxiv.org/abs/2504.00921v1)|null|

|**2025-04-01**|**Exploring Personalized Federated Learning Architectures for Violence Detection in Surveillance Videos**|Mohammad Kassir et.al.|[2504.00857v1](http://arxiv.org/abs/2504.00857v1)|null|

|**2025-04-01**|**Global Intervention and Distillation for Federated Out-of-Distribution Generalization**|Zhuang Qi et.al.|[2504.00850v1](http://arxiv.org/abs/2504.00850v1)|null|

|**2025-04-01**|**Optimizing Resource Allocation and Energy Efficiency in Federated Fog Computing for IoT**|Syed Sarmad Shah et.al.|[2504.00791v1](http://arxiv.org/abs/2504.00791v1)|null|

|**2025-04-01**|**EMO: Edge Model Overlays to Scale Model Size in Federated Learning**|Di Wu et.al.|[2504.00726v1](http://arxiv.org/abs/2504.00726v1)|null|

|**2025-04-01**|**Adaptive Federated Learning with Functional Encryption: A Comparison of Classical and Quantum-safe Options**|Enrico Sorbera et.al.|[2504.00563v1](http://arxiv.org/abs/2504.00563v1)|null|

|**2025-04-01**|**Informed Greedy Algorithm for Scalable Bayesian Network Fusion via Minimum Cut Analysis**|Pablo Torrijos et.al.|[2504.00467v1](http://arxiv.org/abs/2504.00467v1)|null|

|**2025-04-01**|**FedPaI: Achieving Extreme Sparsity in Federated Learning via Pruning at Initialization**|Haonan Wang et.al.|[2504.00308v1](http://arxiv.org/abs/2504.00308v1)|null|

|**2025-03-31**|**Federated Learning for Cross-Domain Data Privacy: A Distributed Approach to Secure Collaboration**|Yiwei Zhang et.al.|[2504.00282v1](http://arxiv.org/abs/2504.00282v1)|null|

|**2025-03-31**|**RailGoerl24: Görlitz Rail Test Center CV Dataset 2024**|Rustam Tagiew et.al.|[2504.00204v1](http://arxiv.org/abs/2504.00204v1)|null|

|**2025-03-31**|**Few-Shot Generation of Brain Tumors for Secure and Fair Data Sharing**|Yongyi Shi et.al.|[2504.00150v1](http://arxiv.org/abs/2504.00150v1)|null|

|**2025-03-31**|**Navigating Decentralized Online Social Networks: An Overview of Technical and Societal Challenges in Architectural Choices**|Ujun Jeong et.al.|[2504.00071v1](http://arxiv.org/abs/2504.00071v1)|null|

|**2025-03-31**|**Federated Structured Sparse PCA for Anomaly Detection in IoT Networks**|Chenyi Huang et.al.|[2503.23981v1](http://arxiv.org/abs/2503.23981v1)|null|

|**2025-03-31**|**Communication-Efficient and Personalized Federated Foundation Model Fine-Tuning via Tri-Matrix Adaptation**|Yongle Li et.al.|[2503.23869v1](http://arxiv.org/abs/2503.23869v1)|null|

|**2025-03-31**|**Blockchain for Federated Learning in the Internet of Things: Trustworthy Adaptation, Standards, and the Road Ahead**|Farhana Javed et.al.|[2503.23823v1](http://arxiv.org/abs/2503.23823v1)|null|

|**2025-03-30**|**Buffer is All You Need: Defending Federated Learning against Backdoor Attacks under Non-iids via Buffering**|Xingyu Lyu et.al.|[2503.23511v1](http://arxiv.org/abs/2503.23511v1)|null|

|**2025-03-30**|**Federated Self-Supervised Learning for One-Shot Cross-Modal and Cross-Imaging Technique Segmentation**|Siladittya Manna et.al.|[2503.23507v1](http://arxiv.org/abs/2503.23507v1)|null|

|**2025-03-30**|**A Systematic Decade Review of Trip Route Planning with Travel Time Estimation based on User Preferences and Behavior**|Nikil Jayasuriya et.al.|[2503.23486v1](http://arxiv.org/abs/2503.23486v1)|null|

### Dataset

|Publish Date|Title|Authors|PDF|Code|

| :---: | :---: | :---: | :---: | :---: |

|**2025-04-02**|**Efficient Federated Learning Tiny Language Models for Mobile Network Feature Prediction**|Daniel Becking et.al.|[2504.01947v1](http://arxiv.org/abs/2504.01947v1)|null|

|**2025-04-02**|**Client Selection in Federated Learning with Data Heterogeneity and Network Latencies**|Harsh Vardhan et.al.|[2504.01921v1](http://arxiv.org/abs/2504.01921v1)|null|

|**2025-04-02**|**CO-DEFEND: Continuous Decentralized Federated Learning for Secure DoH-Based Threat Detection**|Diego Cajaraville-Aboy et.al.|[2504.01882v1](http://arxiv.org/abs/2504.01882v1)|null|

|**2025-04-02**|**A Randomized Zeroth-Order Hierarchical Framework for Heterogeneous Federated Learning**|Yuyang Qiu et.al.|[2504.01839v1](http://arxiv.org/abs/2504.01839v1)|null|

|**2025-04-02**|**A Two-Timescale Approach for Wireless Federated Learning with Parameter Freezing and Power Control**|Jinhao Ouyang et.al.|[2504.01752v1](http://arxiv.org/abs/2504.01752v1)|null|

|**2025-04-02**|**Sky of Unlearning (SoUL): Rewiring Federated Machine Unlearning via Selective Pruning**|Md Mahabub Uz Zaman et.al.|[2504.01705v1](http://arxiv.org/abs/2504.01705v1)|null|

|**2025-04-02**|**Satellite Edge Artificial Intelligence with Large Models: Architectures and Technologies**|Yuanming Shi et.al.|[2504.01676v1](http://arxiv.org/abs/2504.01676v1)|null|

|**2025-04-02**|**Accelerating the discovery of high-performance nonlinear optical materials using active learning and high-throughput screening**|Victor Trinquet et.al.|[2504.01526v1](http://arxiv.org/abs/2504.01526v1)|null|

|**2025-04-02**|**Split Federated Learning for UAV-Enabled Integrated Sensing, Computation, and Communication**|Xiangwang Hou et.al.|[2504.01443v1](http://arxiv.org/abs/2504.01443v1)|null|

|**2025-04-02**|**Age-Aware Partial Gradient Update Strategy for Federated Learning Over the Air**|Ruihao Du et.al.|[2504.01357v1](http://arxiv.org/abs/2504.01357v1)|null|

|**2025-04-01**|**Towards Resilient Federated Learning in CyberEdge Networks: Recent Advances and Future Trends**|Kai Li et.al.|[2504.01240v1](http://arxiv.org/abs/2504.01240v1)|null|

|**2025-04-01**|**Personalized Federated Training of Diffusion Models with Privacy Guarantees**|Kumar Kshitij Patel et.al.|[2504.00952v1](http://arxiv.org/abs/2504.00952v1)|null|

|**2025-04-01**|**Benchmarking Federated Machine Unlearning methods for Tabular Data**|Chenguang Xiao et.al.|[2504.00921v1](http://arxiv.org/abs/2504.00921v1)|null|

|**2025-04-01**|**Exploring Personalized Federated Learning Architectures for Violence Detection in Surveillance Videos**|Mohammad Kassir et.al.|[2504.00857v1](http://arxiv.org/abs/2504.00857v1)|null|

|**2025-04-01**|**Global Intervention and Distillation for Federated Out-of-Distribution Generalization**|Zhuang Qi et.al.|[2504.00850v1](http://arxiv.org/abs/2504.00850v1)|null|

|**2025-04-01**|**Optimizing Resource Allocation and Energy Efficiency in Federated Fog Computing for IoT**|Syed Sarmad Shah et.al.|[2504.00791v1](http://arxiv.org/abs/2504.00791v1)|null|

|**2025-04-01**|**EMO: Edge Model Overlays to Scale Model Size in Federated Learning**|Di Wu et.al.|[2504.00726v1](http://arxiv.org/abs/2504.00726v1)|null|

|**2025-04-01**|**Adaptive Federated Learning with Functional Encryption: A Comparison of Classical and Quantum-safe Options**|Enrico Sorbera et.al.|[2504.00563v1](http://arxiv.org/abs/2504.00563v1)|null|

|**2025-04-01**|**Informed Greedy Algorithm for Scalable Bayesian Network Fusion via Minimum Cut Analysis**|Pablo Torrijos et.al.|[2504.00467v1](http://arxiv.org/abs/2504.00467v1)|null|

|**2025-04-01**|**FedPaI: Achieving Extreme Sparsity in Federated Learning via Pruning at Initialization**|Haonan Wang et.al.|[2504.00308v1](http://arxiv.org/abs/2504.00308v1)|null|

|**2025-03-31**|**Federated Learning for Cross-Domain Data Privacy: A Distributed Approach to Secure Collaboration**|Yiwei Zhang et.al.|[2504.00282v1](http://arxiv.org/abs/2504.00282v1)|null|

|**2025-03-31**|**RailGoerl24: Görlitz Rail Test Center CV Dataset 2024**|Rustam Tagiew et.al.|[2504.00204v1](http://arxiv.org/abs/2504.00204v1)|null|

|**2025-03-31**|**Few-Shot Generation of Brain Tumors for Secure and Fair Data Sharing**|Yongyi Shi et.al.|[2504.00150v1](http://arxiv.org/abs/2504.00150v1)|null|

|**2025-03-31**|**Navigating Decentralized Online Social Networks: An Overview of Technical and Societal Challenges in Architectural Choices**|Ujun Jeong et.al.|[2504.00071v1](http://arxiv.org/abs/2504.00071v1)|null|

|**2025-03-31**|**Federated Structured Sparse PCA for Anomaly Detection in IoT Networks**|Chenyi Huang et.al.|[2503.23981v1](http://arxiv.org/abs/2503.23981v1)|null|

|**2025-03-31**|**Communication-Efficient and Personalized Federated Foundation Model Fine-Tuning via Tri-Matrix Adaptation**|Yongle Li et.al.|[2503.23869v1](http://arxiv.org/abs/2503.23869v1)|null|

|**2025-03-31**|**Blockchain for Federated Learning in the Internet of Things: Trustworthy Adaptation, Standards, and the Road Ahead**|Farhana Javed et.al.|[2503.23823v1](http://arxiv.org/abs/2503.23823v1)|null|

|**2025-03-30**|**Buffer is All You Need: Defending Federated Learning against Backdoor Attacks under Non-iids via Buffering**|Xingyu Lyu et.al.|[2503.23511v1](http://arxiv.org/abs/2503.23511v1)|null|

|**2025-03-30**|**Federated Self-Supervised Learning for One-Shot Cross-Modal and Cross-Imaging Technique Segmentation**|Siladittya Manna et.al.|[2503.23507v1](http://arxiv.org/abs/2503.23507v1)|null|

|**2025-03-30**|**A Systematic Decade Review of Trip Route Planning with Travel Time Estimation based on User Preferences and Behavior**|Nikil Jayasuriya et.al.|[2503.23486v1](http://arxiv.org/abs/2503.23486v1)|null|

### Optimization

|Publish Date|Title|Authors|PDF|Code|

| :---: | :---: | :---: | :---: | :---: |

|**2025-04-02**|**Efficient Federated Learning Tiny Language Models for Mobile Network Feature Prediction**|Daniel Becking et.al.|[2504.01947v1](http://arxiv.org/abs/2504.01947v1)|null|

|**2025-04-02**|**Client Selection in Federated Learning with Data Heterogeneity and Network Latencies**|Harsh Vardhan et.al.|[2504.01921v1](http://arxiv.org/abs/2504.01921v1)|null|

|**2025-04-02**|**CO-DEFEND: Continuous Decentralized Federated Learning for Secure DoH-Based Threat Detection**|Diego Cajaraville-Aboy et.al.|[2504.01882v1](http://arxiv.org/abs/2504.01882v1)|null|

|**2025-04-02**|**A Randomized Zeroth-Order Hierarchical Framework for Heterogeneous Federated Learning**|Yuyang Qiu et.al.|[2504.01839v1](http://arxiv.org/abs/2504.01839v1)|null|

|**2025-04-02**|**A Two-Timescale Approach for Wireless Federated Learning with Parameter Freezing and Power Control**|Jinhao Ouyang et.al.|[2504.01752v1](http://arxiv.org/abs/2504.01752v1)|null|

|**2025-04-02**|**Sky of Unlearning (SoUL): Rewiring Federated Machine Unlearning via Selective Pruning**|Md Mahabub Uz Zaman et.al.|[2504.01705v1](http://arxiv.org/abs/2504.01705v1)|null|

|**2025-04-02**|**Satellite Edge Artificial Intelligence with Large Models: Architectures and Technologies**|Yuanming Shi et.al.|[2504.01676v1](http://arxiv.org/abs/2504.01676v1)|null|

|**2025-04-02**|**Accelerating the discovery of high-performance nonlinear optical materials using active learning and high-throughput screening**|Victor Trinquet et.al.|[2504.01526v1](http://arxiv.org/abs/2504.01526v1)|null|

|**2025-04-02**|**Split Federated Learning for UAV-Enabled Integrated Sensing, Computation, and Communication**|Xiangwang Hou et.al.|[2504.01443v1](http://arxiv.org/abs/2504.01443v1)|null|

|**2025-04-02**|**Age-Aware Partial Gradient Update Strategy for Federated Learning Over the Air**|Ruihao Du et.al.|[2504.01357v1](http://arxiv.org/abs/2504.01357v1)|null|

|**2025-04-01**|**Towards Resilient Federated Learning in CyberEdge Networks: Recent Advances and Future Trends**|Kai Li et.al.|[2504.01240v1](http://arxiv.org/abs/2504.01240v1)|null|

|**2025-04-01**|**Personalized Federated Training of Diffusion Models with Privacy Guarantees**|Kumar Kshitij Patel et.al.|[2504.00952v1](http://arxiv.org/abs/2504.00952v1)|null|

|**2025-04-01**|**Benchmarking Federated Machine Unlearning methods for Tabular Data**|Chenguang Xiao et.al.|[2504.00921v1](http://arxiv.org/abs/2504.00921v1)|null|

|**2025-04-01**|**Exploring Personalized Federated Learning Architectures for Violence Detection in Surveillance Videos**|Mohammad Kassir et.al.|[2504.00857v1](http://arxiv.org/abs/2504.00857v1)|null|

|**2025-04-01**|**Global Intervention and Distillation for Federated Out-of-Distribution Generalization**|Zhuang Qi et.al.|[2504.00850v1](http://arxiv.org/abs/2504.00850v1)|null|

|**2025-04-01**|**Optimizing Resource Allocation and Energy Efficiency in Federated Fog Computing for IoT**|Syed Sarmad Shah et.al.|[2504.00791v1](http://arxiv.org/abs/2504.00791v1)|null|

|**2025-04-01**|**EMO: Edge Model Overlays to Scale Model Size in Federated Learning**|Di Wu et.al.|[2504.00726v1](http://arxiv.org/abs/2504.00726v1)|null|

|**2025-04-01**|**Adaptive Federated Learning with Functional Encryption: A Comparison of Classical and Quantum-safe Options**|Enrico Sorbera et.al.|[2504.00563v1](http://arxiv.org/abs/2504.00563v1)|null|

|**2025-04-01**|**Informed Greedy Algorithm for Scalable Bayesian Network Fusion via Minimum Cut Analysis**|Pablo Torrijos et.al.|[2504.00467v1](http://arxiv.org/abs/2504.00467v1)|null|

|**2025-04-01**|**FedPaI: Achieving Extreme Sparsity in Federated Learning via Pruning at Initialization**|Haonan Wang et.al.|[2504.00308v1](http://arxiv.org/abs/2504.00308v1)|null|

|**2025-03-31**|**Federated Learning for Cross-Domain Data Privacy: A Distributed Approach to Secure Collaboration**|Yiwei Zhang et.al.|[2504.00282v1](http://arxiv.org/abs/2504.00282v1)|null|

|**2025-03-31**|**RailGoerl24: Görlitz Rail Test Center CV Dataset 2024**|Rustam Tagiew et.al.|[2504.00204v1](http://arxiv.org/abs/2504.00204v1)|null|

|**2025-03-31**|**Few-Shot Generation of Brain Tumors for Secure and Fair Data Sharing**|Yongyi Shi et.al.|[2504.00150v1](http://arxiv.org/abs/2504.00150v1)|null|

|**2025-03-31**|**Navigating Decentralized Online Social Networks: An Overview of Technical and Societal Challenges in Architectural Choices**|Ujun Jeong et.al.|[2504.00071v1](http://arxiv.org/abs/2504.00071v1)|null|

|**2025-03-31**|**Federated Structured Sparse PCA for Anomaly Detection in IoT Networks**|Chenyi Huang et.al.|[2503.23981v1](http://arxiv.org/abs/2503.23981v1)|null|

|**2025-03-31**|**Communication-Efficient and Personalized Federated Foundation Model Fine-Tuning via Tri-Matrix Adaptation**|Yongle Li et.al.|[2503.23869v1](http://arxiv.org/abs/2503.23869v1)|null|

|**2025-03-31**|**Blockchain for Federated Learning in the Internet of Things: Trustworthy Adaptation, Standards, and the Road Ahead**|Farhana Javed et.al.|[2503.23823v1](http://arxiv.org/abs/2503.23823v1)|null|

|**2025-03-30**|**Buffer is All You Need: Defending Federated Learning against Backdoor Attacks under Non-iids via Buffering**|Xingyu Lyu et.al.|[2503.23511v1](http://arxiv.org/abs/2503.23511v1)|null|

|**2025-03-30**|**Federated Self-Supervised Learning for One-Shot Cross-Modal and Cross-Imaging Technique Segmentation**|Siladittya Manna et.al.|[2503.23507v1](http://arxiv.org/abs/2503.23507v1)|null|

|**2025-03-30**|**A Systematic Decade Review of Trip Route Planning with Travel Time Estimation based on User Preferences and Behavior**|Nikil Jayasuriya et.al.|[2503.23486v1](http://arxiv.org/abs/2503.23486v1)|null|

### Framework

|Publish Date|Title|Authors|PDF|Code|

| :---: | :---: | :---: | :---: | :---: |

|**2025-04-02**|**Efficient Federated Learning Tiny Language Models for Mobile Network Feature Prediction**|Daniel Becking et.al.|[2504.01947v1](http://arxiv.org/abs/2504.01947v1)|null|

|**2025-04-02**|**Client Selection in Federated Learning with Data Heterogeneity and Network Latencies**|Harsh Vardhan et.al.|[2504.01921v1](http://arxiv.org/abs/2504.01921v1)|null|

|**2025-04-02**|**CO-DEFEND: Continuous Decentralized Federated Learning for Secure DoH-Based Threat Detection**|Diego Cajaraville-Aboy et.al.|[2504.01882v1](http://arxiv.org/abs/2504.01882v1)|null|

|**2025-04-02**|**A Randomized Zeroth-Order Hierarchical Framework for Heterogeneous Federated Learning**|Yuyang Qiu et.al.|[2504.01839v1](http://arxiv.org/abs/2504.01839v1)|null|

|**2025-04-02**|**A Two-Timescale Approach for Wireless Federated Learning with Parameter Freezing and Power Control**|Jinhao Ouyang et.al.|[2504.01752v1](http://arxiv.org/abs/2504.01752v1)|null|

|**2025-04-02**|**Sky of Unlearning (SoUL): Rewiring Federated Machine Unlearning via Selective Pruning**|Md Mahabub Uz Zaman et.al.|[2504.01705v1](http://arxiv.org/abs/2504.01705v1)|null|

|**2025-04-02**|**Satellite Edge Artificial Intelligence with Large Models: Architectures and Technologies**|Yuanming Shi et.al.|[2504.01676v1](http://arxiv.org/abs/2504.01676v1)|null|

|**2025-04-02**|**Accelerating the discovery of high-performance nonlinear optical materials using active learning and high-throughput screening**|Victor Trinquet et.al.|[2504.01526v1](http://arxiv.org/abs/2504.01526v1)|null|

|**2025-04-02**|**Split Federated Learning for UAV-Enabled Integrated Sensing, Computation, and Communication**|Xiangwang Hou et.al.|[2504.01443v1](http://arxiv.org/abs/2504.01443v1)|null|

|**2025-04-02**|**Age-Aware Partial Gradient Update Strategy for Federated Learning Over the Air**|Ruihao Du et.al.|[2504.01357v1](http://arxiv.org/abs/2504.01357v1)|null|

|**2025-04-01**|**Towards Resilient Federated Learning in CyberEdge Networks: Recent Advances and Future Trends**|Kai Li et.al.|[2504.01240v1](http://arxiv.org/abs/2504.01240v1)|null|

|**2025-04-01**|**Personalized Federated Training of Diffusion Models with Privacy Guarantees**|Kumar Kshitij Patel et.al.|[2504.00952v1](http://arxiv.org/abs/2504.00952v1)|null|

|**2025-04-01**|**Benchmarking Federated Machine Unlearning methods for Tabular Data**|Chenguang Xiao et.al.|[2504.00921v1](http://arxiv.org/abs/2504.00921v1)|null|

|**2025-04-01**|**Exploring Personalized Federated Learning Architectures for Violence Detection in Surveillance Videos**|Mohammad Kassir et.al.|[2504.00857v1](http://arxiv.org/abs/2504.00857v1)|null|

|**2025-04-01**|**Global Intervention and Distillation for Federated Out-of-Distribution Generalization**|Zhuang Qi et.al.|[2504.00850v1](http://arxiv.org/abs/2504.00850v1)|null|

|**2025-04-01**|**Optimizing Resource Allocation and Energy Efficiency in Federated Fog Computing for IoT**|Syed Sarmad Shah et.al.|[2504.00791v1](http://arxiv.org/abs/2504.00791v1)|null|

|**2025-04-01**|**EMO: Edge Model Overlays to Scale Model Size in Federated Learning**|Di Wu et.al.|[2504.00726v1](http://arxiv.org/abs/2504.00726v1)|null|

|**2025-04-01**|**Adaptive Federated Learning with Functional Encryption: A Comparison of Classical and Quantum-safe Options**|Enrico Sorbera et.al.|[2504.00563v1](http://arxiv.org/abs/2504.00563v1)|null|

|**2025-04-01**|**Informed Greedy Algorithm for Scalable Bayesian Network Fusion via Minimum Cut Analysis**|Pablo Torrijos et.al.|[2504.00467v1](http://arxiv.org/abs/2504.00467v1)|null|

|**2025-04-01**|**FedPaI: Achieving Extreme Sparsity in Federated Learning via Pruning at Initialization**|Haonan Wang et.al.|[2504.00308v1](http://arxiv.org/abs/2504.00308v1)|null|

|**2025-03-31**|**Federated Learning for Cross-Domain Data Privacy: A Distributed Approach to Secure Collaboration**|Yiwei Zhang et.al.|[2504.00282v1](http://arxiv.org/abs/2504.00282v1)|null|

|**2025-03-31**|**RailGoerl24: Görlitz Rail Test Center CV Dataset 2024**|Rustam Tagiew et.al.|[2504.00204v1](http://arxiv.org/abs/2504.00204v1)|null|

|**2025-03-31**|**Few-Shot Generation of Brain Tumors for Secure and Fair Data Sharing**|Yongyi Shi et.al.|[2504.00150v1](http://arxiv.org/abs/2504.00150v1)|null|

|**2025-03-31**|**Navigating Decentralized Online Social Networks: An Overview of Technical and Societal Challenges in Architectural Choices**|Ujun Jeong et.al.|[2504.00071v1](http://arxiv.org/abs/2504.00071v1)|null|

|**2025-03-31**|**Federated Structured Sparse PCA for Anomaly Detection in IoT Networks**|Chenyi Huang et.al.|[2503.23981v1](http://arxiv.org/abs/2503.23981v1)|null|

|**2025-03-31**|**Communication-Efficient and Personalized Federated Foundation Model Fine-Tuning via Tri-Matrix Adaptation**|Yongle Li et.al.|[2503.23869v1](http://arxiv.org/abs/2503.23869v1)|null|

|**2025-03-31**|**Blockchain for Federated Learning in the Internet of Things: Trustworthy Adaptation, Standards, and the Road Ahead**|Farhana Javed et.al.|[2503.23823v1](http://arxiv.org/abs/2503.23823v1)|null|

|**2025-03-30**|**Buffer is All You Need: Defending Federated Learning against Backdoor Attacks under Non-iids via Buffering**|Xingyu Lyu et.al.|[2503.23511v1](http://arxiv.org/abs/2503.23511v1)|null|

|**2025-03-30**|**Federated Self-Supervised Learning for One-Shot Cross-Modal and Cross-Imaging Technique Segmentation**|Siladittya Manna et.al.|[2503.23507v1](http://arxiv.org/abs/2503.23507v1)|null|

|**2025-03-30**|**A Systematic Decade Review of Trip Route Planning with Travel Time Estimation based on User Preferences and Behavior**|Nikil Jayasuriya et.al.|[2503.23486v1](http://arxiv.org/abs/2503.23486v1)|null|

### Benchmark

|Publish Date|Title|Authors|PDF|Code|

| :---: | :---: | :---: | :---: | :---: |

|**2025-04-02**|**Efficient Federated Learning Tiny Language Models for Mobile Network Feature Prediction**|Daniel Becking et.al.|[2504.01947v1](http://arxiv.org/abs/2504.01947v1)|null|

|**2025-04-02**|**Client Selection in Federated Learning with Data Heterogeneity and Network Latencies**|Harsh Vardhan et.al.|[2504.01921v1](http://arxiv.org/abs/2504.01921v1)|null|

|**2025-04-02**|**CO-DEFEND: Continuous Decentralized Federated Learning for Secure DoH-Based Threat Detection**|Diego Cajaraville-Aboy et.al.|[2504.01882v1](http://arxiv.org/abs/2504.01882v1)|null|

|**2025-04-02**|**A Randomized Zeroth-Order Hierarchical Framework for Heterogeneous Federated Learning**|Yuyang Qiu et.al.|[2504.01839v1](http://arxiv.org/abs/2504.01839v1)|null|

|**2025-04-02**|**A Two-Timescale Approach for Wireless Federated Learning with Parameter Freezing and Power Control**|Jinhao Ouyang et.al.|[2504.01752v1](http://arxiv.org/abs/2504.01752v1)|null|

|**2025-04-02**|**Sky of Unlearning (SoUL): Rewiring Federated Machine Unlearning via Selective Pruning**|Md Mahabub Uz Zaman et.al.|[2504.01705v1](http://arxiv.org/abs/2504.01705v1)|null|

|**2025-04-02**|**Satellite Edge Artificial Intelligence with Large Models: Architectures and Technologies**|Yuanming Shi et.al.|[2504.01676v1](http://arxiv.org/abs/2504.01676v1)|null|

|**2025-04-02**|**Accelerating the discovery of high-performance nonlinear optical materials using active learning and high-throughput screening**|Victor Trinquet et.al.|[2504.01526v1](http://arxiv.org/abs/2504.01526v1)|null|

|**2025-04-02**|**Split Federated Learning for UAV-Enabled Integrated Sensing, Computation, and Communication**|Xiangwang Hou et.al.|[2504.01443v1](http://arxiv.org/abs/2504.01443v1)|null|

|**2025-04-02**|**Age-Aware Partial Gradient Update Strategy for Federated Learning Over the Air**|Ruihao Du et.al.|[2504.01357v1](http://arxiv.org/abs/2504.01357v1)|null|

|**2025-04-01**|**Towards Resilient Federated Learning in CyberEdge Networks: Recent Advances and Future Trends**|Kai Li et.al.|[2504.01240v1](http://arxiv.org/abs/2504.01240v1)|null|

|**2025-04-01**|**Personalized Federated Training of Diffusion Models with Privacy Guarantees**|Kumar Kshitij Patel et.al.|[2504.00952v1](http://arxiv.org/abs/2504.00952v1)|null|

|**2025-04-01**|**Benchmarking Federated Machine Unlearning methods for Tabular Data**|Chenguang Xiao et.al.|[2504.00921v1](http://arxiv.org/abs/2504.00921v1)|null|

|**2025-04-01**|**Exploring Personalized Federated Learning Architectures for Violence Detection in Surveillance Videos**|Mohammad Kassir et.al.|[2504.00857v1](http://arxiv.org/abs/2504.00857v1)|null|

|**2025-04-01**|**Global Intervention and Distillation for Federated Out-of-Distribution Generalization**|Zhuang Qi et.al.|[2504.00850v1](http://arxiv.org/abs/2504.00850v1)|null|

|**2025-04-01**|**Optimizing Resource Allocation and Energy Efficiency in Federated Fog Computing for IoT**|Syed Sarmad Shah et.al.|[2504.00791v1](http://arxiv.org/abs/2504.00791v1)|null|

|**2025-04-01**|**EMO: Edge Model Overlays to Scale Model Size in Federated Learning**|Di Wu et.al.|[2504.00726v1](http://arxiv.org/abs/2504.00726v1)|null|

|**2025-04-01**|**Adaptive Federated Learning with Functional Encryption: A Comparison of Classical and Quantum-safe Options**|Enrico Sorbera et.al.|[2504.00563v1](http://arxiv.org/abs/2504.00563v1)|null|

|**2025-04-01**|**Informed Greedy Algorithm for Scalable Bayesian Network Fusion via Minimum Cut Analysis**|Pablo Torrijos et.al.|[2504.00467v1](http://arxiv.org/abs/2504.00467v1)|null|

|**2025-04-01**|**FedPaI: Achieving Extreme Sparsity in Federated Learning via Pruning at Initialization**|Haonan Wang et.al.|[2504.00308v1](http://arxiv.org/abs/2504.00308v1)|null|

|**2025-03-31**|**Federated Learning for Cross-Domain Data Privacy: A Distributed Approach to Secure Collaboration**|Yiwei Zhang et.al.|[2504.00282v1](http://arxiv.org/abs/2504.00282v1)|null|

|**2025-03-31**|**RailGoerl24: Görlitz Rail Test Center CV Dataset 2024**|Rustam Tagiew et.al.|[2504.00204v1](http://arxiv.org/abs/2504.00204v1)|null|

|**2025-03-31**|**Few-Shot Generation of Brain Tumors for Secure and Fair Data Sharing**|Yongyi Shi et.al.|[2504.00150v1](http://arxiv.org/abs/2504.00150v1)|null|

|**2025-03-31**|**Navigating Decentralized Online Social Networks: An Overview of Technical and Societal Challenges in Architectural Choices**|Ujun Jeong et.al.|[2504.00071v1](http://arxiv.org/abs/2504.00071v1)|null|

|**2025-03-31**|**Federated Structured Sparse PCA for Anomaly Detection in IoT Networks**|Chenyi Huang et.al.|[2503.23981v1](http://arxiv.org/abs/2503.23981v1)|null|

|**2025-03-31**|**Communication-Efficient and Personalized Federated Foundation Model Fine-Tuning via Tri-Matrix Adaptation**|Yongle Li et.al.|[2503.23869v1](http://arxiv.org/abs/2503.23869v1)|null|

|**2025-03-31**|**Blockchain for Federated Learning in the Internet of Things: Trustworthy Adaptation, Standards, and the Road Ahead**|Farhana Javed et.al.|[2503.23823v1](http://arxiv.org/abs/2503.23823v1)|null|

|**2025-03-30**|**Buffer is All You Need: Defending Federated Learning against Backdoor Attacks under Non-iids via Buffering**|Xingyu Lyu et.al.|[2503.23511v1](http://arxiv.org/abs/2503.23511v1)|null|

|**2025-03-30**|**Federated Self-Supervised Learning for One-Shot Cross-Modal and Cross-Imaging Technique Segmentation**|Siladittya Manna et.al.|[2503.23507v1](http://arxiv.org/abs/2503.23507v1)|null|

|**2025-03-30**|**A Systematic Decade Review of Trip Route Planning with Travel Time Estimation based on User Preferences and Behavior**|Nikil Jayasuriya et.al.|[2503.23486v1](http://arxiv.org/abs/2503.23486v1)|null|

## Few-shot Learning

### One-shot Learning

|Publish Date|Title|Authors|PDF|Code|

| :---: | :---: | :---: | :---: | :---: |

|**2025-04-02**|**Learning from Streaming Video with Orthogonal Gradients**|Tengda Han et.al.|[2504.01961v1](http://arxiv.org/abs/2504.01961v1)|null|

|**2025-04-02**|**Diffusion-Guided Gaussian Splatting for Large-Scale Unconstrained 3D Reconstruction and Novel View Synthesis**|Niluthpol Chowdhury Mithun et.al.|[2504.01960v1](http://arxiv.org/abs/2504.01960v1)|null|

|**2025-04-02**|**Slot-Level Robotic Placement via Visual Imitation from Single Human Video**|Dandan Shan et.al.|[2504.01959v1](http://arxiv.org/abs/2504.01959v1)|null|

|**2025-04-02**|**Toward Real-world BEV Perception: Depth Uncertainty Estimation via Gaussian Splatting**|Shu-Wei Lu et.al.|[2504.01957v2](http://arxiv.org/abs/2504.01957v2)|null|

|**2025-04-02**|**Deep Representation Learning for Unsupervised Clustering of Myocardial Fiber Trajectories in Cardiac Diffusion Tensor Imaging**|Mohini Anand et.al.|[2504.01953v1](http://arxiv.org/abs/2504.01953v1)|null|

|**2025-04-02**|**Efficient Federated Learning Tiny Language Models for Mobile Network Feature Prediction**|Daniel Becking et.al.|[2504.01947v1](http://arxiv.org/abs/2504.01947v1)|null|

|**2025-04-02**|**OpenCodeReasoning: Advancing Data Distillation for Competitive Coding**|Wasi Uddin Ahmad et.al.|[2504.01943v1](http://arxiv.org/abs/2504.01943v1)|null|

|**2025-04-02**|**Strengthening Multi-Robot Systems for SAR: Co-Designing Robotics and Communication Towards 6G**|Juan Bravo-Arrabal et.al.|[2504.01940v1](http://arxiv.org/abs/2504.01940v1)|null|

|**2025-04-02**|**A Unified Approach to Analysis and Design of Denoising Markov Models**|Yinuo Ren et.al.|[2504.01938v1](http://arxiv.org/abs/2504.01938v1)|null|

|**2025-04-02**|**Fermionic Averaged Circuit Eigenvalue Sampling**|Adrian Chapman et.al.|[2504.01936v1](http://arxiv.org/abs/2504.01936v1)|null|

|**2025-04-02**|**Hessian-aware Training for Enhancing DNNs Resilience to Parameter Corruptions**|Tahmid Hasan Prato et.al.|[2504.01933v1](http://arxiv.org/abs/2504.01933v1)|null|

|**2025-04-02**|**Is the Reversal Curse a Binding Problem? Uncovering Limitations of Transformers from a Basic Generalization Failure**|Boshi Wang et.al.|[2504.01928v1](http://arxiv.org/abs/2504.01928v1)|null|

|**2025-04-02**|**Gen-C: Populating Virtual Worlds with Generative Crowds**|Andreas Panayiotou et.al.|[2504.01924v1](http://arxiv.org/abs/2504.01924v1)|null|

|**2025-04-02**|**Client Selection in Federated Learning with Data Heterogeneity and Network Latencies**|Harsh Vardhan et.al.|[2504.01921v1](http://arxiv.org/abs/2504.01921v1)|null|

|**2025-04-02**|**Overcoming Deceptiveness in Fitness Optimization with Unsupervised Quality-Diversity**|Lisa Coiffard et.al.|[2504.01915v1](http://arxiv.org/abs/2504.01915v1)|null|

|**2025-04-02**|**Representing Flow Fields with Divergence-Free Kernels for Reconstruction**|Xingyu Ni et.al.|[2504.01913v1](http://arxiv.org/abs/2504.01913v1)|null|

|**2025-04-02**|**Benchmarking Synthetic Tabular Data: A Multi-Dimensional Evaluation Framework**|Andrey Sidorenko et.al.|[2504.01908v1](http://arxiv.org/abs/2504.01908v1)|[link](https://github.com/mostly-ai/mostlyai-qa)|

|**2025-04-02**|**Accelerating IoV Intrusion Detection: Benchmarking GPU-Accelerated vs CPU-Based ML Libraries**|Furkan Çolhak et.al.|[2504.01905v2](http://arxiv.org/abs/2504.01905v2)|null|

|**2025-04-02**|**Graphically Speaking: Unmasking Abuse in Social Media with Conversation Insights**|Célia Nouri et.al.|[2504.01902v1](http://arxiv.org/abs/2504.01902v1)|null|

|**2025-04-02**|**Analysis of an Idealized Stochastic Polyak Method and its Application to Black-Box Model Distillation**|Robert M. Gower et.al.|[2504.01898v1](http://arxiv.org/abs/2504.01898v1)|null|

|**2025-04-02**|**Composition Design of Shape Memory Ceramics based on Gaussian Processes**|Ashutosh Pandey et.al.|[2504.01896v1](http://arxiv.org/abs/2504.01896v1)|null|

|**2025-04-02**|**Multi-fidelity Parameter Estimation Using Conditional Diffusion Models**|Caroline Tatsuoka et.al.|[2504.01894v1](http://arxiv.org/abs/2504.01894v1)|null|

|**2025-04-02**|**Is Temporal Prompting All We Need For Limited Labeled Action Recognition?**|Shreyank N Gowda et.al.|[2504.01890v1](http://arxiv.org/abs/2504.01890v1)|null|

|**2025-04-02**|**GMAI-VL-R1: Harnessing Reinforcement Learning for Multimodal Medical Reasoning**|Yanzhou Su et.al.|[2504.01886v1](http://arxiv.org/abs/2504.01886v1)|null|

|**2025-04-02**|**CoRAG: Collaborative Retrieval-Augmented Generation**|Aashiq Muhamed et.al.|[2504.01883v1](http://arxiv.org/abs/2504.01883v1)|null|

|**2025-04-02**|**CO-DEFEND: Continuous Decentralized Federated Learning for Secure DoH-Based Threat Detection**|Diego Cajaraville-Aboy et.al.|[2504.01882v1](http://arxiv.org/abs/2504.01882v1)|null|

|**2025-04-02**|**Architect Your Landscape Approach (AYLA) for Optimizations in Deep Learning**|Ben Keslaki et.al.|[2504.01875v1](http://arxiv.org/abs/2504.01875v1)|null|

|**2025-04-02**|**Interpreting Emergent Planning in Model-Free Reinforcement Learning**|Thomas Bush et.al.|[2504.01871v1](http://arxiv.org/abs/2504.01871v1)|null|

|**2025-04-02**|**Buggin: Automatic intrinsic bugs classification model using NLP and ML**|Pragya Bhandari et.al.|[2504.01869v1](http://arxiv.org/abs/2504.01869v1)|null|

|**2025-04-02**|**Extending MovieLens-32M to Provide New Evaluation Objectives**|Mark D. Smucker et.al.|[2504.01863v1](http://arxiv.org/abs/2504.01863v1)|null|

### Few-shot Learning

|Publish Date|Title|Authors|PDF|Code|

| :---: | :---: | :---: | :---: | :---: |

|**2025-04-02**|**Learning from Streaming Video with Orthogonal Gradients**|Tengda Han et.al.|[2504.01961v1](http://arxiv.org/abs/2504.01961v1)|null|

|**2025-04-02**|**Diffusion-Guided Gaussian Splatting for Large-Scale Unconstrained 3D Reconstruction and Novel View Synthesis**|Niluthpol Chowdhury Mithun et.al.|[2504.01960v1](http://arxiv.org/abs/2504.01960v1)|null|

|**2025-04-02**|**Slot-Level Robotic Placement via Visual Imitation from Single Human Video**|Dandan Shan et.al.|[2504.01959v1](http://arxiv.org/abs/2504.01959v1)|null|

|**2025-04-02**|**Toward Real-world BEV Perception: Depth Uncertainty Estimation via Gaussian Splatting**|Shu-Wei Lu et.al.|[2504.01957v2](http://arxiv.org/abs/2504.01957v2)|null|

|**2025-04-02**|**Deep Representation Learning for Unsupervised Clustering of Myocardial Fiber Trajectories in Cardiac Diffusion Tensor Imaging**|Mohini Anand et.al.|[2504.01953v1](http://arxiv.org/abs/2504.01953v1)|null|

|**2025-04-02**|**Efficient Federated Learning Tiny Language Models for Mobile Network Feature Prediction**|Daniel Becking et.al.|[2504.01947v1](http://arxiv.org/abs/2504.01947v1)|null|

|**2025-04-02**|**OpenCodeReasoning: Advancing Data Distillation for Competitive Coding**|Wasi Uddin Ahmad et.al.|[2504.01943v1](http://arxiv.org/abs/2504.01943v1)|null|

|**2025-04-02**|**Strengthening Multi-Robot Systems for SAR: Co-Designing Robotics and Communication Towards 6G**|Juan Bravo-Arrabal et.al.|[2504.01940v1](http://arxiv.org/abs/2504.01940v1)|null|

|**2025-04-02**|**A Unified Approach to Analysis and Design of Denoising Markov Models**|Yinuo Ren et.al.|[2504.01938v1](http://arxiv.org/abs/2504.01938v1)|null|

|**2025-04-02**|**Fermionic Averaged Circuit Eigenvalue Sampling**|Adrian Chapman et.al.|[2504.01936v1](http://arxiv.org/abs/2504.01936v1)|null|

|**2025-04-02**|**Hessian-aware Training for Enhancing DNNs Resilience to Parameter Corruptions**|Tahmid Hasan Prato et.al.|[2504.01933v1](http://arxiv.org/abs/2504.01933v1)|null|

|**2025-04-02**|**Is the Reversal Curse a Binding Problem? Uncovering Limitations of Transformers from a Basic Generalization Failure**|Boshi Wang et.al.|[2504.01928v1](http://arxiv.org/abs/2504.01928v1)|null|

|**2025-04-02**|**Gen-C: Populating Virtual Worlds with Generative Crowds**|Andreas Panayiotou et.al.|[2504.01924v1](http://arxiv.org/abs/2504.01924v1)|null|

|**2025-04-02**|**Client Selection in Federated Learning with Data Heterogeneity and Network Latencies**|Harsh Vardhan et.al.|[2504.01921v1](http://arxiv.org/abs/2504.01921v1)|null|

|**2025-04-02**|**Overcoming Deceptiveness in Fitness Optimization with Unsupervised Quality-Diversity**|Lisa Coiffard et.al.|[2504.01915v1](http://arxiv.org/abs/2504.01915v1)|null|

|**2025-04-02**|**Representing Flow Fields with Divergence-Free Kernels for Reconstruction**|Xingyu Ni et.al.|[2504.01913v1](http://arxiv.org/abs/2504.01913v1)|null|

|**2025-04-02**|**Benchmarking Synthetic Tabular Data: A Multi-Dimensional Evaluation Framework**|Andrey Sidorenko et.al.|[2504.01908v1](http://arxiv.org/abs/2504.01908v1)|[link](https://github.com/mostly-ai/mostlyai-qa)|

|**2025-04-02**|**Accelerating IoV Intrusion Detection: Benchmarking GPU-Accelerated vs CPU-Based ML Libraries**|Furkan Çolhak et.al.|[2504.01905v2](http://arxiv.org/abs/2504.01905v2)|null|

|**2025-04-02**|**Graphically Speaking: Unmasking Abuse in Social Media with Conversation Insights**|Célia Nouri et.al.|[2504.01902v1](http://arxiv.org/abs/2504.01902v1)|null|

|**2025-04-02**|**Analysis of an Idealized Stochastic Polyak Method and its Application to Black-Box Model Distillation**|Robert M. Gower et.al.|[2504.01898v1](http://arxiv.org/abs/2504.01898v1)|null|

|**2025-04-02**|**Composition Design of Shape Memory Ceramics based on Gaussian Processes**|Ashutosh Pandey et.al.|[2504.01896v1](http://arxiv.org/abs/2504.01896v1)|null|

|**2025-04-02**|**Multi-fidelity Parameter Estimation Using Conditional Diffusion Models**|Caroline Tatsuoka et.al.|[2504.01894v1](http://arxiv.org/abs/2504.01894v1)|null|

|**2025-04-02**|**Is Temporal Prompting All We Need For Limited Labeled Action Recognition?**|Shreyank N Gowda et.al.|[2504.01890v1](http://arxiv.org/abs/2504.01890v1)|null|

|**2025-04-02**|**GMAI-VL-R1: Harnessing Reinforcement Learning for Multimodal Medical Reasoning**|Yanzhou Su et.al.|[2504.01886v1](http://arxiv.org/abs/2504.01886v1)|null|

|**2025-04-02**|**CoRAG: Collaborative Retrieval-Augmented Generation**|Aashiq Muhamed et.al.|[2504.01883v1](http://arxiv.org/abs/2504.01883v1)|null|

|**2025-04-02**|**CO-DEFEND: Continuous Decentralized Federated Learning for Secure DoH-Based Threat Detection**|Diego Cajaraville-Aboy et.al.|[2504.01882v1](http://arxiv.org/abs/2504.01882v1)|null|

|**2025-04-02**|**Architect Your Landscape Approach (AYLA) for Optimizations in Deep Learning**|Ben Keslaki et.al.|[2504.01875v1](http://arxiv.org/abs/2504.01875v1)|null|

|**2025-04-02**|**Interpreting Emergent Planning in Model-Free Reinforcement Learning**|Thomas Bush et.al.|[2504.01871v1](http://arxiv.org/abs/2504.01871v1)|null|

|**2025-04-02**|**Buggin: Automatic intrinsic bugs classification model using NLP and ML**|Pragya Bhandari et.al.|[2504.01869v1](http://arxiv.org/abs/2504.01869v1)|null|

|**2025-04-02**|**Extending MovieLens-32M to Provide New Evaluation Objectives**|Mark D. Smucker et.al.|[2504.01863v1](http://arxiv.org/abs/2504.01863v1)|null|

### Meta Learning

|Publish Date|Title|Authors|PDF|Code|

| :---: | :---: | :---: | :---: | :---: |

|**2025-04-02**|**Sparse Gaussian Neural Processes**|Tommy Rochussen et.al.|[2504.01650v1](http://arxiv.org/abs/2504.01650v1)|null|

|**2025-04-02**|**Cat-Eye Inspired Active-Passive-Composite Aperture-Shared Sub-Terahertz Meta-Imager for Non-Interactive Concealed Object Detection**|Mingshuang Hu et.al.|[2504.01473v1](http://arxiv.org/abs/2504.01473v1)|null|

|**2025-04-02**|**Enabling Systematic Generalization in Abstract Spatial Reasoning through Meta-Learning for Compositionality**|Philipp Mondorf et.al.|[2504.01445v1](http://arxiv.org/abs/2504.01445v1)|null|

|**2025-04-02**|**Virtual Reality and Artificial Intelligence as Psychological Countermeasures in Space and Other Isolated and Confined Environments: A Scoping Review**|Jennifer Sharp et.al.|[2504.01366v1](http://arxiv.org/abs/2504.01366v1)|null|

|**2025-04-01**|**Prompting Forgetting: Unlearning in GANs via Textual Guidance**|Piyush Nagasubramaniam et.al.|[2504.01218v1](http://arxiv.org/abs/2504.01218v1)|null|

|**2025-04-01**|**New Improvements in Solving Large LABS Instances Using Massively Parallelizable Memetic Tabu Search**|Zhiwei Zhang et.al.|[2504.00987v1](http://arxiv.org/abs/2504.00987v1)|null|

|**2025-04-01**|**Sim-is-More: Randomizing HW-NAS with Synthetic Devices**|Francesco Capuano et.al.|[2504.00663v1](http://arxiv.org/abs/2504.00663v1)|null|

|**2025-04-01**|**Towards Responsible and Trustworthy Educational Data Mining: Comparing Symbolic, Sub-Symbolic, and Neural-Symbolic AI Methods**|Danial Hooshyar et.al.|[2504.00615v1](http://arxiv.org/abs/2504.00615v1)|null|

|**2025-04-01**|**Meta-learning for cosmological emulation: Rapid adaptation to new lensing kernels**|Charlie MacMahon-Gellér et.al.|[2504.00552v1](http://arxiv.org/abs/2504.00552v1)|null|

|**2025-04-01**|**MetaLoRA: Tensor-Enhanced Adaptive Low-Rank Fine-tuning**|Maolin Wang et.al.|[2504.00460v1](http://arxiv.org/abs/2504.00460v1)|null|

|**2025-04-01**|**Efficient and Sustainable Task Offloading in UAV-Assisted MEC Systems via Meta Deep Reinforcement Learning**|Maryam Farajzadeh Dehkordi et.al.|[2504.00453v1](http://arxiv.org/abs/2504.00453v1)|null|

|**2025-04-01**|**VerifiAgent: a Unified Verification Agent in Language Model Reasoning**|Jiuzhou Han et.al.|[2504.00406v1](http://arxiv.org/abs/2504.00406v1)|null|

|**2025-03-31**|**MetaCLBench: Meta Continual Learning Benchmark on Resource-Constrained Edge Devices**|Sijia Li et.al.|[2504.00174v1](http://arxiv.org/abs/2504.00174v1)|null|

|**2025-03-31**|**Performance analysis of metasurface-based spatial multimode transmission for 6G wireless communications**|Ju Yong Lee et.al.|[2504.00137v1](http://arxiv.org/abs/2504.00137v1)|null|

|**2025-03-31**|**What the F*ck Is Artificial General Intelligence?**|Michael Timothy Bennett et.al.|[2503.23923v1](http://arxiv.org/abs/2503.23923v1)|null|

|**2025-03-30**|**A Systematic Decade Review of Trip Route Planning with Travel Time Estimation based on User Preferences and Behavior**|Nikil Jayasuriya et.al.|[2503.23486v1](http://arxiv.org/abs/2503.23486v1)|null|

|**2025-03-30**|**Meta-Ori: monolithic meta-origami for nonlinear inflatable soft actuators**|Hugo de Souza Oliveira et.al.|[2503.23375v1](http://arxiv.org/abs/2503.23375v1)|null|

|**2025-03-30**|**Linguistic Loops and Geometric Invariants as a Way to Pre-Verbal Thought?**|Daniele Corradetti et.al.|[2503.23311v1](http://arxiv.org/abs/2503.23311v1)|null|

|**2025-03-30**|**SalesRLAgent: A Reinforcement Learning Approach for Real-Time Sales Conversion Prediction and Optimization**|Nandakishor M et.al.|[2503.23303v1](http://arxiv.org/abs/2503.23303v1)|null|

|**2025-03-29**|**Convolutional Neural Networks Can (Meta-)Learn the Same-Different Relation**|Max Gupta et.al.|[2503.23212v2](http://arxiv.org/abs/2503.23212v2)|null|

|**2025-03-29**|**Importance of bond exchange in MnC structural stability and half-metallic ferromagnetism: a comprehensive density functional benchmark study**|Abdesalem Houari et.al.|[2503.23116v1](http://arxiv.org/abs/2503.23116v1)|null|

|**2025-03-28**|**Optimal treatment regimes for the net benefit of a treatment**|François Petit et.al.|[2503.22580v1](http://arxiv.org/abs/2503.22580v1)|null|

|**2025-03-28**|**Terahertz frequency-domain 4x4 Mueller matrix ellipsometer instrument designed for high-frequency magnetic resonance measurements**|Viktor Rindert et.al.|[2503.22500v1](http://arxiv.org/abs/2503.22500v1)|null|

|**2025-03-28**|**Chaos in violent relaxation dynamics. Disentangling micro- and macro-chaos in numerical experiments of dissipationless collapse**|Simone Sartorello et.al.|[2503.22479v1](http://arxiv.org/abs/2503.22479v1)|null|

|**2025-03-28**|**Meta-LoRA: Meta-Learning LoRA Components for Domain-Aware ID Personalization**|Barış Batuhan Topal et.al.|[2503.22352v1](http://arxiv.org/abs/2503.22352v1)|null|

|**2025-03-28**|**Polarization Decoupling Multi-Port Beam-Splitting Metasurface for Miniaturized Magneto-Optical Trap**|Tian Tian et.al.|[2503.22167v2](http://arxiv.org/abs/2503.22167v2)|null|

|**2025-03-27**|**HyperMAN: Hypergraph-enhanced Meta-learning Adaptive Network for Next POI Recommendation**|Jinze Wang et.al.|[2503.22049v1](http://arxiv.org/abs/2503.22049v1)|[link](https://github.com/ICME-2025/HyperMAN)|

|**2025-03-27**|**Fractal Countability as a Constructive Alternative to the Power Set of N: A Meta-Formal Approach to Stratified Definability**|Stanislav Semenov et.al.|[2503.22042v1](http://arxiv.org/abs/2503.22042v1)|null|

|**2025-03-27**|**Reward Design for Reinforcement Learning Agents**|Rati Devidze et.al.|[2503.21949v1](http://arxiv.org/abs/2503.21949v1)|[link](https://github.com/adishs/neurips2021_explicable-reward-design_code)|

|**2025-03-27**|**DSU-Net:An Improved U-Net Model Based on DINOv2 and SAM2 with Multi-scale Cross-model Feature Enhancement**|Yimin Xu et.al.|[2503.21187v2](http://arxiv.org/abs/2503.21187v2)|[link](https://github.com/cheneyxuyimin/sam2dino-seg)|

## Transfer Learning

### Transfer Learning

|Publish Date|Title|Authors|PDF|Code|

| :---: | :---: | :---: | :---: | :---: |

|**2025-04-02**|**Learning from Streaming Video with Orthogonal Gradients**|Tengda Han et.al.|[2504.01961v1](http://arxiv.org/abs/2504.01961v1)|null|

|**2025-04-02**|**Diffusion-Guided Gaussian Splatting for Large-Scale Unconstrained 3D Reconstruction and Novel View Synthesis**|Niluthpol Chowdhury Mithun et.al.|[2504.01960v1](http://arxiv.org/abs/2504.01960v1)|null|

|**2025-04-02**|**Slot-Level Robotic Placement via Visual Imitation from Single Human Video**|Dandan Shan et.al.|[2504.01959v1](http://arxiv.org/abs/2504.01959v1)|null|

|**2025-04-02**|**Toward Real-world BEV Perception: Depth Uncertainty Estimation via Gaussian Splatting**|Shu-Wei Lu et.al.|[2504.01957v2](http://arxiv.org/abs/2504.01957v2)|null|

|**2025-04-02**|**Deep Representation Learning for Unsupervised Clustering of Myocardial Fiber Trajectories in Cardiac Diffusion Tensor Imaging**|Mohini Anand et.al.|[2504.01953v1](http://arxiv.org/abs/2504.01953v1)|null|

|**2025-04-02**|**Efficient Federated Learning Tiny Language Models for Mobile Network Feature Prediction**|Daniel Becking et.al.|[2504.01947v1](http://arxiv.org/abs/2504.01947v1)|null|

|**2025-04-02**|**OpenCodeReasoning: Advancing Data Distillation for Competitive Coding**|Wasi Uddin Ahmad et.al.|[2504.01943v1](http://arxiv.org/abs/2504.01943v1)|null|

|**2025-04-02**|**Strengthening Multi-Robot Systems for SAR: Co-Designing Robotics and Communication Towards 6G**|Juan Bravo-Arrabal et.al.|[2504.01940v1](http://arxiv.org/abs/2504.01940v1)|null|

|**2025-04-02**|**A Unified Approach to Analysis and Design of Denoising Markov Models**|Yinuo Ren et.al.|[2504.01938v1](http://arxiv.org/abs/2504.01938v1)|null|

|**2025-04-02**|**Fermionic Averaged Circuit Eigenvalue Sampling**|Adrian Chapman et.al.|[2504.01936v1](http://arxiv.org/abs/2504.01936v1)|null|

|**2025-04-02**|**Hessian-aware Training for Enhancing DNNs Resilience to Parameter Corruptions**|Tahmid Hasan Prato et.al.|[2504.01933v1](http://arxiv.org/abs/2504.01933v1)|null|

|**2025-04-02**|**Is the Reversal Curse a Binding Problem? Uncovering Limitations of Transformers from a Basic Generalization Failure**|Boshi Wang et.al.|[2504.01928v1](http://arxiv.org/abs/2504.01928v1)|null|

|**2025-04-02**|**Gen-C: Populating Virtual Worlds with Generative Crowds**|Andreas Panayiotou et.al.|[2504.01924v1](http://arxiv.org/abs/2504.01924v1)|null|

|**2025-04-02**|**Client Selection in Federated Learning with Data Heterogeneity and Network Latencies**|Harsh Vardhan et.al.|[2504.01921v1](http://arxiv.org/abs/2504.01921v1)|null|

|**2025-04-02**|**Bridging the Linguistic Divide: A Survey on Leveraging Large Language Models for Machine Translation**|Baban Gain et.al.|[2504.01919v2](http://arxiv.org/abs/2504.01919v2)|null|

|**2025-04-02**|**Overcoming Deceptiveness in Fitness Optimization with Unsupervised Quality-Diversity**|Lisa Coiffard et.al.|[2504.01915v1](http://arxiv.org/abs/2504.01915v1)|null|

|**2025-04-02**|**Representing Flow Fields with Divergence-Free Kernels for Reconstruction**|Xingyu Ni et.al.|[2504.01913v1](http://arxiv.org/abs/2504.01913v1)|null|

|**2025-04-02**|**Benchmarking Synthetic Tabular Data: A Multi-Dimensional Evaluation Framework**|Andrey Sidorenko et.al.|[2504.01908v1](http://arxiv.org/abs/2504.01908v1)|[link](https://github.com/mostly-ai/mostlyai-qa)|

|**2025-04-02**|**Accelerating IoV Intrusion Detection: Benchmarking GPU-Accelerated vs CPU-Based ML Libraries**|Furkan Çolhak et.al.|[2504.01905v2](http://arxiv.org/abs/2504.01905v2)|null|

|**2025-04-02**|**A Dilaton Sum Rule for the Conformal Anomaly Form Factor in QCD at Order $α_s$**|Claudio Corianò et.al.|[2504.01904v1](http://arxiv.org/abs/2504.01904v1)|null|

|**2025-04-02**|**Graphically Speaking: Unmasking Abuse in Social Media with Conversation Insights**|Célia Nouri et.al.|[2504.01902v1](http://arxiv.org/abs/2504.01902v1)|null|

|**2025-04-02**|**Analysis of an Idealized Stochastic Polyak Method and its Application to Black-Box Model Distillation**|Robert M. Gower et.al.|[2504.01898v1](http://arxiv.org/abs/2504.01898v1)|null|

|**2025-04-02**|**Composition Design of Shape Memory Ceramics based on Gaussian Processes**|Ashutosh Pandey et.al.|[2504.01896v1](http://arxiv.org/abs/2504.01896v1)|null|

|**2025-04-02**|**Multi-fidelity Parameter Estimation Using Conditional Diffusion Models**|Caroline Tatsuoka et.al.|[2504.01894v1](http://arxiv.org/abs/2504.01894v1)|null|

|**2025-04-02**|**Is Temporal Prompting All We Need For Limited Labeled Action Recognition?**|Shreyank N Gowda et.al.|[2504.01890v1](http://arxiv.org/abs/2504.01890v1)|null|

|**2025-04-02**|**GMAI-VL-R1: Harnessing Reinforcement Learning for Multimodal Medical Reasoning**|Yanzhou Su et.al.|[2504.01886v1](http://arxiv.org/abs/2504.01886v1)|null|

|**2025-04-02**|**CoRAG: Collaborative Retrieval-Augmented Generation**|Aashiq Muhamed et.al.|[2504.01883v1](http://arxiv.org/abs/2504.01883v1)|null|

|**2025-04-02**|**CO-DEFEND: Continuous Decentralized Federated Learning for Secure DoH-Based Threat Detection**|Diego Cajaraville-Aboy et.al.|[2504.01882v1](http://arxiv.org/abs/2504.01882v1)|null|

|**2025-04-02**|**Architect Your Landscape Approach (AYLA) for Optimizations in Deep Learning**|Ben Keslaki et.al.|[2504.01875v1](http://arxiv.org/abs/2504.01875v1)|null|

|**2025-04-02**|**Interpreting Emergent Planning in Model-Free Reinforcement Learning**|Thomas Bush et.al.|[2504.01871v1](http://arxiv.org/abs/2504.01871v1)|null|

## Unsupervised Learning

### Unsupervised Learning

|Publish Date|Title|Authors|PDF|Code|

| :---: | :---: | :---: | :---: | :---: |

|**2025-04-02**|**Learning from Streaming Video with Orthogonal Gradients**|Tengda Han et.al.|[2504.01961v1](http://arxiv.org/abs/2504.01961v1)|null|

|**2025-04-02**|**Diffusion-Guided Gaussian Splatting for Large-Scale Unconstrained 3D Reconstruction and Novel View Synthesis**|Niluthpol Chowdhury Mithun et.al.|[2504.01960v1](http://arxiv.org/abs/2504.01960v1)|null|

|**2025-04-02**|**Slot-Level Robotic Placement via Visual Imitation from Single Human Video**|Dandan Shan et.al.|[2504.01959v1](http://arxiv.org/abs/2504.01959v1)|null|

|**2025-04-02**|**Toward Real-world BEV Perception: Depth Uncertainty Estimation via Gaussian Splatting**|Shu-Wei Lu et.al.|[2504.01957v2](http://arxiv.org/abs/2504.01957v2)|null|

|**2025-04-02**|**Scene-Centric Unsupervised Panoptic Segmentation**|Oliver Hahn et.al.|[2504.01955v1](http://arxiv.org/abs/2504.01955v1)|null|

|**2025-04-02**|**Deep Representation Learning for Unsupervised Clustering of Myocardial Fiber Trajectories in Cardiac Diffusion Tensor Imaging**|Mohini Anand et.al.|[2504.01953v1](http://arxiv.org/abs/2504.01953v1)|null|

|**2025-04-02**|**Efficient Federated Learning Tiny Language Models for Mobile Network Feature Prediction**|Daniel Becking et.al.|[2504.01947v1](http://arxiv.org/abs/2504.01947v1)|null|

|**2025-04-02**|**OpenCodeReasoning: Advancing Data Distillation for Competitive Coding**|Wasi Uddin Ahmad et.al.|[2504.01943v1](http://arxiv.org/abs/2504.01943v1)|null|

|**2025-04-02**|**Strengthening Multi-Robot Systems for SAR: Co-Designing Robotics and Communication Towards 6G**|Juan Bravo-Arrabal et.al.|[2504.01940v1](http://arxiv.org/abs/2504.01940v1)|null|

|**2025-04-02**|**A Unified Approach to Analysis and Design of Denoising Markov Models**|Yinuo Ren et.al.|[2504.01938v1](http://arxiv.org/abs/2504.01938v1)|null|

|**2025-04-02**|**Fermionic Averaged Circuit Eigenvalue Sampling**|Adrian Chapman et.al.|[2504.01936v1](http://arxiv.org/abs/2504.01936v1)|null|

|**2025-04-02**|**Hessian-aware Training for Enhancing DNNs Resilience to Parameter Corruptions**|Tahmid Hasan Prato et.al.|[2504.01933v1](http://arxiv.org/abs/2504.01933v1)|null|

|**2025-04-02**|**Is the Reversal Curse a Binding Problem? Uncovering Limitations of Transformers from a Basic Generalization Failure**|Boshi Wang et.al.|[2504.01928v1](http://arxiv.org/abs/2504.01928v1)|null|

|**2025-04-02**|**Gen-C: Populating Virtual Worlds with Generative Crowds**|Andreas Panayiotou et.al.|[2504.01924v1](http://arxiv.org/abs/2504.01924v1)|null|

|**2025-04-02**|**Client Selection in Federated Learning with Data Heterogeneity and Network Latencies**|Harsh Vardhan et.al.|[2504.01921v1](http://arxiv.org/abs/2504.01921v1)|null|

|**2025-04-02**|**Overcoming Deceptiveness in Fitness Optimization with Unsupervised Quality-Diversity**|Lisa Coiffard et.al.|[2504.01915v1](http://arxiv.org/abs/2504.01915v1)|null|

|**2025-04-02**|**Representing Flow Fields with Divergence-Free Kernels for Reconstruction**|Xingyu Ni et.al.|[2504.01913v1](http://arxiv.org/abs/2504.01913v1)|null|

|**2025-04-02**|**Benchmarking Synthetic Tabular Data: A Multi-Dimensional Evaluation Framework**|Andrey Sidorenko et.al.|[2504.01908v1](http://arxiv.org/abs/2504.01908v1)|[link](https://github.com/mostly-ai/mostlyai-qa)|

|**2025-04-02**|**Accelerating IoV Intrusion Detection: Benchmarking GPU-Accelerated vs CPU-Based ML Libraries**|Furkan Çolhak et.al.|[2504.01905v2](http://arxiv.org/abs/2504.01905v2)|null|

|**2025-04-02**|**Graphically Speaking: Unmasking Abuse in Social Media with Conversation Insights**|Célia Nouri et.al.|[2504.01902v1](http://arxiv.org/abs/2504.01902v1)|null|

|**2025-04-02**|**Analysis of an Idealized Stochastic Polyak Method and its Application to Black-Box Model Distillation**|Robert M. Gower et.al.|[2504.01898v1](http://arxiv.org/abs/2504.01898v1)|null|

|**2025-04-02**|**Composition Design of Shape Memory Ceramics based on Gaussian Processes**|Ashutosh Pandey et.al.|[2504.01896v1](http://arxiv.org/abs/2504.01896v1)|null|

|**2025-04-02**|**Multi-fidelity Parameter Estimation Using Conditional Diffusion Models**|Caroline Tatsuoka et.al.|[2504.01894v1](http://arxiv.org/abs/2504.01894v1)|null|

|**2025-04-02**|**Is Temporal Prompting All We Need For Limited Labeled Action Recognition?**|Shreyank N Gowda et.al.|[2504.01890v1](http://arxiv.org/abs/2504.01890v1)|null|

|**2025-04-02**|**GMAI-VL-R1: Harnessing Reinforcement Learning for Multimodal Medical Reasoning**|Yanzhou Su et.al.|[2504.01886v1](http://arxiv.org/abs/2504.01886v1)|null|

|**2025-04-02**|**CoRAG: Collaborative Retrieval-Augmented Generation**|Aashiq Muhamed et.al.|[2504.01883v1](http://arxiv.org/abs/2504.01883v1)|null|

|**2025-04-02**|**CO-DEFEND: Continuous Decentralized Federated Learning for Secure DoH-Based Threat Detection**|Diego Cajaraville-Aboy et.al.|[2504.01882v1](http://arxiv.org/abs/2504.01882v1)|null|

|**2025-04-02**|**Architect Your Landscape Approach (AYLA) for Optimizations in Deep Learning**|Ben Keslaki et.al.|[2504.01875v1](http://arxiv.org/abs/2504.01875v1)|null|

|**2025-04-02**|**Interpreting Emergent Planning in Model-Free Reinforcement Learning**|Thomas Bush et.al.|[2504.01871v1](http://arxiv.org/abs/2504.01871v1)|null|

|**2025-04-02**|**Buggin: Automatic intrinsic bugs classification model using NLP and ML**|Pragya Bhandari et.al.|[2504.01869v1](http://arxiv.org/abs/2504.01869v1)|null|

### GAN

|Publish Date|Title|Authors|PDF|Code|

| :---: | :---: | :---: | :---: | :---: |

|**2025-04-02**|**VideoScene: Distilling Video Diffusion Model to Generate 3D Scenes in One Step**|Hanyang Wang et.al.|[2504.01956v2](http://arxiv.org/abs/2504.01956v2)|null|

|**2025-04-02**|**Deep Representation Learning for Unsupervised Clustering of Myocardial Fiber Trajectories in Cardiac Diffusion Tensor Imaging**|Mohini Anand et.al.|[2504.01953v1](http://arxiv.org/abs/2504.01953v1)|null|

|**2025-04-02**|**Efficient Federated Learning Tiny Language Models for Mobile Network Feature Prediction**|Daniel Becking et.al.|[2504.01947v1](http://arxiv.org/abs/2504.01947v1)|null|

|**2025-04-02**|**Asynchronous Traffic Shaping and Redundancy: Avoiding Unbounded Latencies in In-Car Networks**|Teresa Lübeck et.al.|[2504.01946v1](http://arxiv.org/abs/2504.01946v1)|null|

|**2025-04-02**|**Graphon games and an idealized limit of large network games**|Motoki Otsuka et.al.|[2504.01944v1](http://arxiv.org/abs/2504.01944v1)|null|

|**2025-04-02**|**Strengthening Multi-Robot Systems for SAR: Co-Designing Robotics and Communication Towards 6G**|Juan Bravo-Arrabal et.al.|[2504.01940v1](http://arxiv.org/abs/2504.01940v1)|null|

|**2025-04-02**|**Hessian-aware Training for Enhancing DNNs Resilience to Parameter Corruptions**|Tahmid Hasan Prato et.al.|[2504.01933v1](http://arxiv.org/abs/2504.01933v1)|null|

|**2025-04-02**|**Equivariant Spherical CNNs for Accurate Fiber Orientation Distribution Estimation in Neonatal Diffusion MRI with Reduced Acquisition Time**|Haykel Snoussi et.al.|[2504.01925v1](http://arxiv.org/abs/2504.01925v1)|null|

|**2025-04-02**|**Gen-C: Populating Virtual Worlds with Generative Crowds**|Andreas Panayiotou et.al.|[2504.01924v1](http://arxiv.org/abs/2504.01924v1)|null|

|**2025-04-02**|**Client Selection in Federated Learning with Data Heterogeneity and Network Latencies**|Harsh Vardhan et.al.|[2504.01921v1](http://arxiv.org/abs/2504.01921v1)|null|

|**2025-04-02**|**Accelerating IoV Intrusion Detection: Benchmarking GPU-Accelerated vs CPU-Based ML Libraries**|Furkan Çolhak et.al.|[2504.01905v2](http://arxiv.org/abs/2504.01905v2)|null|

|**2025-04-02**|**Graphically Speaking: Unmasking Abuse in Social Media with Conversation Insights**|Célia Nouri et.al.|[2504.01902v1](http://arxiv.org/abs/2504.01902v1)|null|

|**2025-04-02**|**Multi-stream Physics Hybrid Networks for solving Navier-Stokes equations**|Tatjana Protasevich et.al.|[2504.01891v1](http://arxiv.org/abs/2504.01891v1)|null|

|**2025-04-02**|**CO-DEFEND: Continuous Decentralized Federated Learning for Secure DoH-Based Threat Detection**|Diego Cajaraville-Aboy et.al.|[2504.01882v1](http://arxiv.org/abs/2504.01882v1)|null|

|**2025-04-02**|**Architect Your Landscape Approach (AYLA) for Optimizations in Deep Learning**|Ben Keslaki et.al.|[2504.01875v1](http://arxiv.org/abs/2504.01875v1)|null|

|**2025-04-02**|**Corner-Grasp: Multi-Action Grasp Detection and Active Gripper Adaptation for Grasping in Cluttered Environments**|Yeong Gwang Son et.al.|[2504.01861v1](http://arxiv.org/abs/2504.01861v1)|null|

|**2025-04-02**|**Lower Bounds for Leader Election and Collective Coin Flipping, Revisited**|Eshan Chattopadhyay et.al.|[2504.01856v1](http://arxiv.org/abs/2504.01856v1)|null|

|**2025-04-02**|**Inference of hidden common driver dynamics by anisotropic self-organizing neural networks**|Zsigmond Benkő et.al.|[2504.01811v1](http://arxiv.org/abs/2504.01811v1)|null|

|**2025-04-02**|**Detector Response to Gravitational Wave Polarizations in Gravitational Quantum Field Theory**|Cong Xu et.al.|[2504.01809v1](http://arxiv.org/abs/2504.01809v1)|null|

|**2025-04-02**|**Distributed Triangle Detection is Hard in Few Rounds**|Sepehr Assadi et.al.|[2504.01802v1](http://arxiv.org/abs/2504.01802v1)|null|

|**2025-04-02**|**A Novel Approach To Implementing Knowledge Distillation In Tsetlin Machines**|Calvin Kinateder et.al.|[2504.01798v1](http://arxiv.org/abs/2504.01798v1)|null|

|**2025-04-02**|**Leveraging Embedding Techniques in Multimodal Machine Learning for Mental Illness Assessment**|Abdelrahaman A. Hassan et.al.|[2504.01767v1](http://arxiv.org/abs/2504.01767v1)|null|

|**2025-04-02**|**KD$^{2}$M: An unifying framework for feature knowledge distillation**|Eduardo Fernandes Montesuma et.al.|[2504.01757v1](http://arxiv.org/abs/2504.01757v1)|null|

|**2025-04-02**|**Bridge the Gap between SNN and ANN for Image Restoration**|Xin Su et.al.|[2504.01755v1](http://arxiv.org/abs/2504.01755v1)|null|

|**2025-04-02**|**Stable Structure Learning with HC-Stable and Tabu-Stable Algorithms**|Neville K. Kitson et.al.|[2504.01740v1](http://arxiv.org/abs/2504.01740v1)|null|

|**2025-04-02**|**Understanding Cross-Model Perceptual Invariances Through Ensemble Metamers**|Lukas Boehm et.al.|[2504.01739v1](http://arxiv.org/abs/2504.01739v1)|null|

|**2025-04-02**|**Enlightenment Period Improving DNN Performance**|Tiantian Liu et.al.|[2504.01737v1](http://arxiv.org/abs/2504.01737v1)|null|

|**2025-04-02**|**AdPO: Enhancing the Adversarial Robustness of Large Vision-Language Models with Preference Optimization**|Chaohu Liu et.al.|[2504.01735v1](http://arxiv.org/abs/2504.01735v1)|null|

|**2025-04-02**|**AI-Driven Framework for Multi-Service Multi-Modal Devices in NextG ORAN Systems**|Mrityunjoy Gain et.al.|[2504.01730v2](http://arxiv.org/abs/2504.01730v2)|null|

|**2025-04-02**|**An Adaptive Proximal Inexact Gradient Framework and Its Application to Per-Antenna Constrained Joint Beamforming and Compression Design**|Xilai Fan et.al.|[2504.01721v1](http://arxiv.org/abs/2504.01721v1)|null|

## Multi-modal

### Vision-Language

|Publish Date|Title|Authors|PDF|Code|

| :---: | :---: | :---: | :---: | :---: |

### Image Caption

|Publish Date|Title|Authors|PDF|Code|

| :---: | :---: | :---: | :---: | :---: |

|**2025-04-02**|**Toward Real-world BEV Perception: Depth Uncertainty Estimation via Gaussian Splatting**|Shu-Wei Lu et.al.|[2504.01957v2](http://arxiv.org/abs/2504.01957v2)|null|

|**2025-04-02**|**Scene-Centric Unsupervised Panoptic Segmentation**|Oliver Hahn et.al.|[2504.01955v1](http://arxiv.org/abs/2504.01955v1)|null|

|**2025-04-02**|**Towards Unified Referring Expression Segmentation Across Omni-Level Visual Target Granularities**|Jing Liu et.al.|[2504.01954v1](http://arxiv.org/abs/2504.01954v1)|null|

|**2025-04-02**|**Deep Representation Learning for Unsupervised Clustering of Myocardial Fiber Trajectories in Cardiac Diffusion Tensor Imaging**|Mohini Anand et.al.|[2504.01953v1](http://arxiv.org/abs/2504.01953v1)|null|

|**2025-04-02**|**Image Difference Grounding with Natural Language**|Wenxuan Wang et.al.|[2504.01952v1](http://arxiv.org/abs/2504.01952v1)|null|

|**2025-04-02**|**End-to-End Driving with Online Trajectory Evaluation via BEV World Model**|Yingyan Li et.al.|[2504.01941v1](http://arxiv.org/abs/2504.01941v1)|null|

|**2025-04-02**|**ILLUME+: Illuminating Unified MLLM with Dual Visual Tokenization and Diffusion Refinement**|Runhui Huang et.al.|[2504.01934v2](http://arxiv.org/abs/2504.01934v2)|null|

|**2025-04-02**|**Equivariant Spherical CNNs for Accurate Fiber Orientation Distribution Estimation in Neonatal Diffusion MRI with Reduced Acquisition Time**|Haykel Snoussi et.al.|[2504.01925v1](http://arxiv.org/abs/2504.01925v1)|null|

|**2025-04-02**|**Is Less Really More? Fake News Detection with Limited Information**|Zhaoyang Cao et.al.|[2504.01922v1](http://arxiv.org/abs/2504.01922v1)|[link](https://github.com/kappakant/SLIM)|

|**2025-04-02**|**FineLIP: Extending CLIP's Reach via Fine-Grained Alignment with Longer Text Inputs**|Mothilal Asokan et.al.|[2504.01916v1](http://arxiv.org/abs/2504.01916v1)|null|

|**2025-04-02**|**Ross3D: Reconstructive Visual Instruction Tuning with 3D-Awareness**|Haochen Wang et.al.|[2504.01901v1](http://arxiv.org/abs/2504.01901v1)|null|

|**2025-04-02**|**GMAI-VL-R1: Harnessing Reinforcement Learning for Multimodal Medical Reasoning**|Yanzhou Su et.al.|[2504.01886v1](http://arxiv.org/abs/2504.01886v1)|null|

|**2025-04-02**|**A Diffusion-Based Framework for Occluded Object Movement**|Zheng-Peng Duan et.al.|[2504.01873v1](http://arxiv.org/abs/2504.01873v1)|null|

|**2025-04-02**|**CoMatcher: Multi-View Collaborative Feature Matching**|Jintao Zhang et.al.|[2504.01872v1](http://arxiv.org/abs/2504.01872v1)|null|

|**2025-04-02**|**Corner-Grasp: Multi-Action Grasp Detection and Active Gripper Adaptation for Grasping in Cluttered Environments**|Yeong Gwang Son et.al.|[2504.01861v1](http://arxiv.org/abs/2504.01861v1)|null|

|**2025-04-02**|**Deciphering the Nature of Virgil: An Obscured AGN Lurking Within an Apparently Normal Lyman-α Emitter During Cosmic Reionization**|Pierluigi Rinaldi et.al.|[2504.01852v1](http://arxiv.org/abs/2504.01852v1)|null|

|**2025-04-02**|**Dust environment of long-period comet C/2023 A3 (Tsuchinshan-ATLAS)**|Fernando Moreno et.al.|[2504.01845v1](http://arxiv.org/abs/2504.01845v1)|null|

|**2025-04-02**|**A Randomized Zeroth-Order Hierarchical Framework for Heterogeneous Federated Learning**|Yuyang Qiu et.al.|[2504.01839v1](http://arxiv.org/abs/2504.01839v1)|null|

|**2025-04-02**|**Prompting Medical Vision-Language Models to Mitigate Diagnosis Bias by Generating Realistic Dermoscopic Images**|Nusrat Munia et.al.|[2504.01838v1](http://arxiv.org/abs/2504.01838v1)|null|

|**2025-04-02**|**Implicit Bias Injection Attacks against Text-to-Image Diffusion Models**|Huayang Huang et.al.|[2504.01819v1](http://arxiv.org/abs/2504.01819v1)|null|

|**2025-04-02**|**A Novel Approach To Implementing Knowledge Distillation In Tsetlin Machines**|Calvin Kinateder et.al.|[2504.01798v1](http://arxiv.org/abs/2504.01798v1)|null|

|**2025-04-02**|**UniViTAR: Unified Vision Transformer with Native Resolution**|Limeng Qiao et.al.|[2504.01792v1](http://arxiv.org/abs/2504.01792v1)|null|

|**2025-04-02**|**Projections from Furstenberg boundaries onto maximal flats and barycenter maps**|Michelle Bucher et.al.|[2504.01788v1](http://arxiv.org/abs/2504.01788v1)|null|

|**2025-04-02**|**Defect detection in III-V multijunction solar cells using reverse-bias stress tests**|Aitana Cano et.al.|[2504.01775v1](http://arxiv.org/abs/2504.01775v1)|null|

|**2025-04-02**|**Bridge the Gap between SNN and ANN for Image Restoration**|Xin Su et.al.|[2504.01755v1](http://arxiv.org/abs/2504.01755v1)|null|

|**2025-04-02**|**Cyanine-Conjugated Gold Nanospheres for Near-infrared Fluorescence**|Neelima Chacko et.al.|[2504.01751v1](http://arxiv.org/abs/2504.01751v1)|null|

|**2025-04-02**|**Universal inverse Radon transforms: Inhomogeneity, angular restrictions and boundary**|I. V. Anikin et.al.|[2504.01744v1](http://arxiv.org/abs/2504.01744v1)|null|

|**2025-04-02**|**Understanding Cross-Model Perceptual Invariances Through Ensemble Metamers**|Lukas Boehm et.al.|[2504.01739v1](http://arxiv.org/abs/2504.01739v1)|null|

|**2025-04-02**|**AdPO: Enhancing the Adversarial Robustness of Large Vision-Language Models with Preference Optimization**|Chaohu Liu et.al.|[2504.01735v1](http://arxiv.org/abs/2504.01735v1)|null|

|**2025-04-02**|**FIORD: A Fisheye Indoor-Outdoor Dataset with LIDAR Ground Truth for 3D Scene Reconstruction and Benchmarking**|Ulas Gunes et.al.|[2504.01732v1](http://arxiv.org/abs/2504.01732v1)|null|

### Multi-modal

|Publish Date|Title|Authors|PDF|Code|

| :---: | :---: | :---: | :---: | :---: |

|**2025-04-02**|**Image Difference Grounding with Natural Language**|Wenxuan Wang et.al.|[2504.01952v1](http://arxiv.org/abs/2504.01952v1)|null|

|**2025-04-02**|**Review, Refine, Repeat: Understanding Iterative Decoding of AI Agents with Dynamic Evaluation and Selection**|Souradip Chakraborty et.al.|[2504.01931v1](http://arxiv.org/abs/2504.01931v1)|null|

|**2025-04-02**|**Is Less Really More? Fake News Detection with Limited Information**|Zhaoyang Cao et.al.|[2504.01922v1](http://arxiv.org/abs/2504.01922v1)|[link](https://github.com/kappakant/SLIM)|

|**2025-04-02**|**FineLIP: Extending CLIP's Reach via Fine-Grained Alignment with Longer Text Inputs**|Mothilal Asokan et.al.|[2504.01916v1](http://arxiv.org/abs/2504.01916v1)|null|

|**2025-04-02**|**Multi-fidelity Parameter Estimation Using Conditional Diffusion Models**|Caroline Tatsuoka et.al.|[2504.01894v1](http://arxiv.org/abs/2504.01894v1)|null|

|**2025-04-02**|**Spatial-R1: Enhancing MLLMs in Video Spatial Reasoning**|Kun Ouyang et.al.|[2504.01805v1](http://arxiv.org/abs/2504.01805v1)|null|

|**2025-04-02**|**UniViTAR: Unified Vision Transformer with Native Resolution**|Limeng Qiao et.al.|[2504.01792v1](http://arxiv.org/abs/2504.01792v1)|null|

|**2025-04-02**|**Leveraging Embedding Techniques in Multimodal Machine Learning for Mental Illness Assessment**|Abdelrahaman A. Hassan et.al.|[2504.01767v1](http://arxiv.org/abs/2504.01767v1)|null|

|**2025-04-02**|**AI-Driven Framework for Multi-Service Multi-Modal Devices in NextG ORAN Systems**|Mrityunjoy Gain et.al.|[2504.01730v2](http://arxiv.org/abs/2504.01730v2)|null|

|**2025-04-02**|**TransforMerger: Transformer-based Voice-Gesture Fusion for Robust Human-Robot Communication**|Petr Vanc et.al.|[2504.01708v1](http://arxiv.org/abs/2504.01708v1)|null|

|**2025-04-02**|**Q-Adapt: Adapting LMM for Visual Quality Assessment with Progressive Instruction Tuning**|Yiting Lu et.al.|[2504.01655v1](http://arxiv.org/abs/2504.01655v1)|null|

|**2025-04-02**|**Propagation of space-time optical vortices in multimode fibers**|Spencer W. Jolly et.al.|[2504.01643v1](http://arxiv.org/abs/2504.01643v1)|null|

|**2025-04-02**|**Bridge 2D-3D: Uncertainty-aware Hierarchical Registration Network with Domain Alignment**|Zhixin Cheng et.al.|[2504.01641v1](http://arxiv.org/abs/2504.01641v1)|null|

|**2025-04-02**|**Leveraging Modality Tags for Enhanced Cross-Modal Video Retrieval**|Adriano Fragomeni et.al.|[2504.01591v2](http://arxiv.org/abs/2504.01591v2)|null|

|**2025-04-02**|**Text Speaks Louder than Vision: ASCII Art Reveals Textual Biases in Vision-Language Models**|Zhaochen Wang et.al.|[2504.01589v1](http://arxiv.org/abs/2504.01589v1)|null|

|**2025-04-02**|**STPNet: Scale-aware Text Prompt Network for Medical Image Segmentation**|Dandan Shan et.al.|[2504.01561v1](http://arxiv.org/abs/2504.01561v1)|null|

|**2025-04-02**|**Semi-Supervised Biomedical Image Segmentation via Diffusion Models and Teacher-Student Co-Training**|Luca Ciampi et.al.|[2504.01547v1](http://arxiv.org/abs/2504.01547v1)|null|

|**2025-04-02**|**Enhanced Cross-modal 3D Retrieval via Tri-modal Reconstruction**|Junlong Ren et.al.|[2504.01476v1](http://arxiv.org/abs/2504.01476v1)|null|

|**2025-04-02**|**Multimodal Point Cloud Semantic Segmentation With Virtual Point Enhancement**|Zaipeng Duan et.al.|[2504.01449v1](http://arxiv.org/abs/2504.01449v1)|null|

|**2025-04-02**|**PiCo: Jailbreaking Multimodal Large Language Models via $\textbf{Pi}$ctorial $\textbf{Co}$de Contextualization**|Aofan Liu et.al.|[2504.01444v1](http://arxiv.org/abs/2504.01444v1)|null|

|**2025-04-02**|**Locally- but not Globally-identified SVARs**|Emanuele Bacchiocchi et.al.|[2504.01441v1](http://arxiv.org/abs/2504.01441v1)|null|

|**2025-04-02**|**DF-Calib: Targetless LiDAR-Camera Calibration via Depth Flow**|Shu Han et.al.|[2504.01416v1](http://arxiv.org/abs/2504.01416v1)|null|

|**2025-04-02**|**Slow-Fast Architecture for Video Multi-Modal Large Language Models**|Min Shi et.al.|[2504.01328v1](http://arxiv.org/abs/2504.01328v1)|null|

|**2025-04-02**|**COST: Contrastive One-Stage Transformer for Vision-Language Small Object Tracking**|Chunhui Zhang et.al.|[2504.01321v1](http://arxiv.org/abs/2504.01321v1)|null|

|**2025-04-02**|**ForestVO: Enhancing Visual Odometry in Forest Environments through ForestGlue**|Thomas Pritchard et.al.|[2504.01261v1](http://arxiv.org/abs/2504.01261v1)|null|

|**2025-04-01**|**Prompting Forgetting: Unlearning in GANs via Textual Guidance**|Piyush Nagasubramaniam et.al.|[2504.01218v1](http://arxiv.org/abs/2504.01218v1)|null|

|**2025-04-01**|**Reset Induced Multimodality in Unbounded Potential**|Karol Capała et.al.|[2504.01200v1](http://arxiv.org/abs/2504.01200v1)|null|

|**2025-04-01**|**Multilingual and Multi-Accent Jailbreaking of Audio LLMs**|Jaechul Roh et.al.|[2504.01094v1](http://arxiv.org/abs/2504.01094v1)|null|

|**2025-04-01**|**HomeEmergency -- Using Audio to Find and Respond to Emergencies in the Home**|James F. Mullen Jr et.al.|[2504.01089v1](http://arxiv.org/abs/2504.01089v1)|null|

|**2025-04-01**|**GECKO: Gigapixel Vision-Concept Contrastive Pretraining in Histopathology**|Saarthak Kapse et.al.|[2504.01009v1](http://arxiv.org/abs/2504.01009v1)|null|

### VQA

|Publish Date|Title|Authors|PDF|Code|

| :---: | :---: | :---: | :---: | :---: |

|**2025-04-02**|**Slot-Level Robotic Placement via Visual Imitation from Single Human Video**|Dandan Shan et.al.|[2504.01959v1](http://arxiv.org/abs/2504.01959v1)|null|

|**2025-04-02**|**VideoScene: Distilling Video Diffusion Model to Generate 3D Scenes in One Step**|Hanyang Wang et.al.|[2504.01956v2](http://arxiv.org/abs/2504.01956v2)|null|

|**2025-04-02**|**The LLM Wears Prada: Analysing Gender Bias and Stereotypes through Online Shopping Data**|Massimiliano Luca et.al.|[2504.01951v1](http://arxiv.org/abs/2504.01951v1)|null|

|**2025-04-02**|**Critical Thinking: Which Kinds of Complexity Govern Optimal Reasoning Length?**|Celine Lee et.al.|[2504.01935v1](http://arxiv.org/abs/2504.01935v1)|null|

|**2025-04-02**|**Hessian-aware Training for Enhancing DNNs Resilience to Parameter Corruptions**|Tahmid Hasan Prato et.al.|[2504.01933v1](http://arxiv.org/abs/2504.01933v1)|null|

|**2025-04-02**|**Review, Refine, Repeat: Understanding Iterative Decoding of AI Agents with Dynamic Evaluation and Selection**|Souradip Chakraborty et.al.|[2504.01931v1](http://arxiv.org/abs/2504.01931v1)|null|

|**2025-04-02**|**Pairing Anderson motives via formal residues in the Frobenius endomorphism**|Quentin Gazda et.al.|[2504.01926v1](http://arxiv.org/abs/2504.01926v1)|null|

|**2025-04-02**|**Representing Flow Fields with Divergence-Free Kernels for Reconstruction**|Xingyu Ni et.al.|[2504.01913v1](http://arxiv.org/abs/2504.01913v1)|null|

|**2025-04-02**|**Multi-fidelity Parameter Estimation Using Conditional Diffusion Models**|Caroline Tatsuoka et.al.|[2504.01894v1](http://arxiv.org/abs/2504.01894v1)|null|

|**2025-04-02**|**GMAI-VL-R1: Harnessing Reinforcement Learning for Multimodal Medical Reasoning**|Yanzhou Su et.al.|[2504.01886v1](http://arxiv.org/abs/2504.01886v1)|null|

|**2025-04-02**|**CoRAG: Collaborative Retrieval-Augmented Generation**|Aashiq Muhamed et.al.|[2504.01883v1](http://arxiv.org/abs/2504.01883v1)|null|

|**2025-04-02**|**TransientTables: Evaluating LLMs' Reasoning on Temporally Evolving Semi-structured Tables**|Abhilash Shankarampeta et.al.|[2504.01879v1](http://arxiv.org/abs/2504.01879v1)|null|

|**2025-04-02**|**CoMatcher: Multi-View Collaborative Feature Matching**|Jintao Zhang et.al.|[2504.01872v1](http://arxiv.org/abs/2504.01872v1)|null|

|**2025-04-02**|**Investigating the Variable Continuum Lags in PG 2130+099**|Jake A. Miller et.al.|[2504.01858v1](http://arxiv.org/abs/2504.01858v1)|null|

|**2025-04-02**|**Cross-Lingual Consistency: A Novel Inference Framework for Advancing Reasoning in Large Language Models**|Zhiwei Yu et.al.|[2504.01857v1](http://arxiv.org/abs/2504.01857v1)|null|

|**2025-04-02**|**Deciphering the Nature of Virgil: An Obscured AGN Lurking Within an Apparently Normal Lyman-α Emitter During Cosmic Reionization**|Pierluigi Rinaldi et.al.|[2504.01852v1](http://arxiv.org/abs/2504.01852v1)|null|

|**2025-04-02**|**Estimating hazard rates from $δ$-records in discrete distributions**|Martín Alcalde et.al.|[2504.01836v1](http://arxiv.org/abs/2504.01836v1)|null|

|**2025-04-02**|**YourBench: Easy Custom Evaluation Sets for Everyone**|Sumuk Shashidhar et.al.|[2504.01833v1](http://arxiv.org/abs/2504.01833v1)|null|

|**2025-04-02**|**What is AI, what is it not, how we use it in physics and how it impacts... you**|Claire David et.al.|[2504.01827v1](http://arxiv.org/abs/2504.01827v1)|null|

|**2025-04-02**|**Inference of hidden common driver dynamics by anisotropic self-organizing neural networks**|Zsigmond Benkő et.al.|[2504.01811v1](http://arxiv.org/abs/2504.01811v1)|null|

|**2025-04-02**|**Barrier Certificates for Unknown Systems with Latent States and Polynomial Dynamics using Bayesian Inference**|Robert Lefringhausen et.al.|[2504.01807v1](http://arxiv.org/abs/2504.01807v1)|null|

|**2025-04-02**|**Quattro: Transformer-Accelerated Iterative Linear Quadratic Regulator Framework for Fast Trajectory Optimization**|Yue Wang et.al.|[2504.01806v1](http://arxiv.org/abs/2504.01806v1)|null|

|**2025-04-02**|**BlenderGym: Benchmarking Foundational Model Systems for Graphics Editing**|Yunqi Gu et.al.|[2504.01786v1](http://arxiv.org/abs/2504.01786v1)|null|

|**2025-04-02**|**Memory-efficient Low-latency Remote Photoplethysmography through Temporal-Spatial State Space Duality**|Kegang Wang et.al.|[2504.01774v1](http://arxiv.org/abs/2504.01774v1)|null|

|**2025-04-02**|**Non-parametric Quantile Regression and Uniform Inference with Unknown Error Distribution**|Haoze Hou et.al.|[2504.01761v1](http://arxiv.org/abs/2504.01761v1)|null|

|**2025-04-02**|**Hidden Markov Model Filtering with Equal Exit Probabilities**|Dongyan Sui et.al.|[2504.01759v1](http://arxiv.org/abs/2504.01759v1)|null|

|**2025-04-02**|**TransforMerger: Transformer-based Voice-Gesture Fusion for Robust Human-Robot Communication**|Petr Vanc et.al.|[2504.01708v1](http://arxiv.org/abs/2504.01708v1)|null|

|**2025-04-02**|**Exact Borel subalgebras of quasi-hereditary monomial algebras**|Anna Rodriguez Rasmussen et.al.|[2504.01706v1](http://arxiv.org/abs/2504.01706v1)|null|

|**2025-04-02**|**A Causal Inference Framework for Data Rich Environments**|Alberto Abadie et.al.|[2504.01702v1](http://arxiv.org/abs/2504.01702v1)|null|

|**2025-04-02**|**Reasoning LLMs for User-Aware Multimodal Conversational Agents**|Hamed Rahimi et.al.|[2504.01700v1](http://arxiv.org/abs/2504.01700v1)|null|

### Alignment

|Publish Date|Title|Authors|PDF|Code|

| :---: | :---: | :---: | :---: | :---: |

|**2025-04-02**|**Image Difference Grounding with Natural Language**|Wenxuan Wang et.al.|[2504.01952v1](http://arxiv.org/abs/2504.01952v1)|null|

|**2025-04-02**|**Review, Refine, Repeat: Understanding Iterative Decoding of AI Agents with Dynamic Evaluation and Selection**|Souradip Chakraborty et.al.|[2504.01931v1](http://arxiv.org/abs/2504.01931v1)|null|

|**2025-04-02**|**Is Less Really More? Fake News Detection with Limited Information**|Zhaoyang Cao et.al.|[2504.01922v1](http://arxiv.org/abs/2504.01922v1)|[link](https://github.com/kappakant/SLIM)|

|**2025-04-02**|**FineLIP: Extending CLIP's Reach via Fine-Grained Alignment with Longer Text Inputs**|Mothilal Asokan et.al.|[2504.01916v1](http://arxiv.org/abs/2504.01916v1)|null|

|**2025-04-02**|**Multi-fidelity Parameter Estimation Using Conditional Diffusion Models**|Caroline Tatsuoka et.al.|[2504.01894v1](http://arxiv.org/abs/2504.01894v1)|null|

|**2025-04-02**|**Spatial-R1: Enhancing MLLMs in Video Spatial Reasoning**|Kun Ouyang et.al.|[2504.01805v1](http://arxiv.org/abs/2504.01805v1)|null|

|**2025-04-02**|**UniViTAR: Unified Vision Transformer with Native Resolution**|Limeng Qiao et.al.|[2504.01792v1](http://arxiv.org/abs/2504.01792v1)|null|

|**2025-04-02**|**Leveraging Embedding Techniques in Multimodal Machine Learning for Mental Illness Assessment**|Abdelrahaman A. Hassan et.al.|[2504.01767v1](http://arxiv.org/abs/2504.01767v1)|null|

|**2025-04-02**|**AI-Driven Framework for Multi-Service Multi-Modal Devices in NextG ORAN Systems**|Mrityunjoy Gain et.al.|[2504.01730v2](http://arxiv.org/abs/2504.01730v2)|null|

|**2025-04-02**|**TransforMerger: Transformer-based Voice-Gesture Fusion for Robust Human-Robot Communication**|Petr Vanc et.al.|[2504.01708v1](http://arxiv.org/abs/2504.01708v1)|null|

|**2025-04-02**|**Q-Adapt: Adapting LMM for Visual Quality Assessment with Progressive Instruction Tuning**|Yiting Lu et.al.|[2504.01655v1](http://arxiv.org/abs/2504.01655v1)|null|

|**2025-04-02**|**Propagation of space-time optical vortices in multimode fibers**|Spencer W. Jolly et.al.|[2504.01643v1](http://arxiv.org/abs/2504.01643v1)|null|

|**2025-04-02**|**Bridge 2D-3D: Uncertainty-aware Hierarchical Registration Network with Domain Alignment**|Zhixin Cheng et.al.|[2504.01641v1](http://arxiv.org/abs/2504.01641v1)|null|

|**2025-04-02**|**Leveraging Modality Tags for Enhanced Cross-Modal Video Retrieval**|Adriano Fragomeni et.al.|[2504.01591v2](http://arxiv.org/abs/2504.01591v2)|null|

|**2025-04-02**|**Text Speaks Louder than Vision: ASCII Art Reveals Textual Biases in Vision-Language Models**|Zhaochen Wang et.al.|[2504.01589v1](http://arxiv.org/abs/2504.01589v1)|null|

|**2025-04-02**|**STPNet: Scale-aware Text Prompt Network for Medical Image Segmentation**|Dandan Shan et.al.|[2504.01561v1](http://arxiv.org/abs/2504.01561v1)|null|

|**2025-04-02**|**Semi-Supervised Biomedical Image Segmentation via Diffusion Models and Teacher-Student Co-Training**|Luca Ciampi et.al.|[2504.01547v1](http://arxiv.org/abs/2504.01547v1)|null|

|**2025-04-02**|**Enhanced Cross-modal 3D Retrieval via Tri-modal Reconstruction**|Junlong Ren et.al.|[2504.01476v1](http://arxiv.org/abs/2504.01476v1)|null|

|**2025-04-02**|**Multimodal Point Cloud Semantic Segmentation With Virtual Point Enhancement**|Zaipeng Duan et.al.|[2504.01449v1](http://arxiv.org/abs/2504.01449v1)|null|

|**2025-04-02**|**PiCo: Jailbreaking Multimodal Large Language Models via $\textbf{Pi}$ctorial $\textbf{Co}$de Contextualization**|Aofan Liu et.al.|[2504.01444v1](http://arxiv.org/abs/2504.01444v1)|null|

|**2025-04-02**|**Locally- but not Globally-identified SVARs**|Emanuele Bacchiocchi et.al.|[2504.01441v1](http://arxiv.org/abs/2504.01441v1)|null|

|**2025-04-02**|**DF-Calib: Targetless LiDAR-Camera Calibration via Depth Flow**|Shu Han et.al.|[2504.01416v1](http://arxiv.org/abs/2504.01416v1)|null|

|**2025-04-02**|**Slow-Fast Architecture for Video Multi-Modal Large Language Models**|Min Shi et.al.|[2504.01328v1](http://arxiv.org/abs/2504.01328v1)|null|

|**2025-04-02**|**COST: Contrastive One-Stage Transformer for Vision-Language Small Object Tracking**|Chunhui Zhang et.al.|[2504.01321v1](http://arxiv.org/abs/2504.01321v1)|null|

|**2025-04-02**|**ForestVO: Enhancing Visual Odometry in Forest Environments through ForestGlue**|Thomas Pritchard et.al.|[2504.01261v1](http://arxiv.org/abs/2504.01261v1)|null|

|**2025-04-01**|**Prompting Forgetting: Unlearning in GANs via Textual Guidance**|Piyush Nagasubramaniam et.al.|[2504.01218v1](http://arxiv.org/abs/2504.01218v1)|null|

|**2025-04-01**|**Reset Induced Multimodality in Unbounded Potential**|Karol Capała et.al.|[2504.01200v1](http://arxiv.org/abs/2504.01200v1)|null|

|**2025-04-01**|**Multilingual and Multi-Accent Jailbreaking of Audio LLMs**|Jaechul Roh et.al.|[2504.01094v1](http://arxiv.org/abs/2504.01094v1)|null|

|**2025-04-01**|**HomeEmergency -- Using Audio to Find and Respond to Emergencies in the Home**|James F. Mullen Jr et.al.|[2504.01089v1](http://arxiv.org/abs/2504.01089v1)|null|

|**2025-04-01**|**GECKO: Gigapixel Vision-Concept Contrastive Pretraining in Histopathology**|Saarthak Kapse et.al.|[2504.01009v1](http://arxiv.org/abs/2504.01009v1)|null|

### Text and Image Generation

|Publish Date|Title|Authors|PDF|Code|

| :---: | :---: | :---: | :---: | :---: |

|**2025-04-02**|**Learning from Streaming Video with Orthogonal Gradients**|Tengda Han et.al.|[2504.01961v1](http://arxiv.org/abs/2504.01961v1)|null|

|**2025-04-02**|**Diffusion-Guided Gaussian Splatting for Large-Scale Unconstrained 3D Reconstruction and Novel View Synthesis**|Niluthpol Chowdhury Mithun et.al.|[2504.01960v1](http://arxiv.org/abs/2504.01960v1)|null|

|**2025-04-02**|**Slot-Level Robotic Placement via Visual Imitation from Single Human Video**|Dandan Shan et.al.|[2504.01959v1](http://arxiv.org/abs/2504.01959v1)|null|

|**2025-04-02**|**Individual halo bias in models of $f(R)$ gravity**|Jorge Enrique García-Farieta et.al.|[2504.01958v1](http://arxiv.org/abs/2504.01958v1)|null|

|**2025-04-02**|**Toward Real-world BEV Perception: Depth Uncertainty Estimation via Gaussian Splatting**|Shu-Wei Lu et.al.|[2504.01957v2](http://arxiv.org/abs/2504.01957v2)|null|

|**2025-04-02**|**VideoScene: Distilling Video Diffusion Model to Generate 3D Scenes in One Step**|Hanyang Wang et.al.|[2504.01956v2](http://arxiv.org/abs/2504.01956v2)|null|

|**2025-04-02**|**Scene-Centric Unsupervised Panoptic Segmentation**|Oliver Hahn et.al.|[2504.01955v1](http://arxiv.org/abs/2504.01955v1)|null|

|**2025-04-02**|**Towards Unified Referring Expression Segmentation Across Omni-Level Visual Target Granularities**|Jing Liu et.al.|[2504.01954v1](http://arxiv.org/abs/2504.01954v1)|null|

|**2025-04-02**|**Deep Representation Learning for Unsupervised Clustering of Myocardial Fiber Trajectories in Cardiac Diffusion Tensor Imaging**|Mohini Anand et.al.|[2504.01953v1](http://arxiv.org/abs/2504.01953v1)|null|

|**2025-04-02**|**Image Difference Grounding with Natural Language**|Wenxuan Wang et.al.|[2504.01952v1](http://arxiv.org/abs/2504.01952v1)|null|

|**2025-04-02**|**The LLM Wears Prada: Analysing Gender Bias and Stereotypes through Online Shopping Data**|Massimiliano Luca et.al.|[2504.01951v1](http://arxiv.org/abs/2504.01951v1)|null|

|**2025-04-02**|**Nucleon scattering from lattice QCD**|Colin Morningstar et.al.|[2504.01950v1](http://arxiv.org/abs/2504.01950v1)|null|

|**2025-04-02**|**Comparison of Bayesian methods for extrapolation of treatment effects: a large scale simulation study**|Tristan Fauvel et.al.|[2504.01949v1](http://arxiv.org/abs/2504.01949v1)|null|

|**2025-04-02**|**PIMDAL: Mitigating the Memory Bottleneck in Data Analytics using a Real Processing-in-Memory System**|Manos Frouzakis et.al.|[2504.01948v1](http://arxiv.org/abs/2504.01948v1)|null|

|**2025-04-02**|**Efficient Federated Learning Tiny Language Models for Mobile Network Feature Prediction**|Daniel Becking et.al.|[2504.01947v1](http://arxiv.org/abs/2504.01947v1)|null|

|**2025-04-02**|**Asynchronous Traffic Shaping and Redundancy: Avoiding Unbounded Latencies in In-Car Networks**|Teresa Lübeck et.al.|[2504.01946v1](http://arxiv.org/abs/2504.01946v1)|null|

|**2025-04-02**|**Graphon games and an idealized limit of large network games**|Motoki Otsuka et.al.|[2504.01944v1](http://arxiv.org/abs/2504.01944v1)|null|

|**2025-04-02**|**OpenCodeReasoning: Advancing Data Distillation for Competitive Coding**|Wasi Uddin Ahmad et.al.|[2504.01943v1](http://arxiv.org/abs/2504.01943v1)|null|

|**2025-04-02**|**De Sitter entropy: on-shell versus off-shell**|Dmitrii Diakonov et.al.|[2504.01942v1](http://arxiv.org/abs/2504.01942v1)|null|

|**2025-04-02**|**End-to-End Driving with Online Trajectory Evaluation via BEV World Model**|Yingyan Li et.al.|[2504.01941v1](http://arxiv.org/abs/2504.01941v1)|null|

|**2025-04-02**|**Strengthening Multi-Robot Systems for SAR: Co-Designing Robotics and Communication Towards 6G**|Juan Bravo-Arrabal et.al.|[2504.01940v1](http://arxiv.org/abs/2504.01940v1)|null|

|**2025-04-02**|**Laboratory evaluation of a wearable instrumented headband for rotational head kinematics measurement**|Anu Tripathi et.al.|[2504.01939v1](http://arxiv.org/abs/2504.01939v1)|null|

|**2025-04-02**|**A Unified Approach to Analysis and Design of Denoising Markov Models**|Yinuo Ren et.al.|[2504.01938v1](http://arxiv.org/abs/2504.01938v1)|null|

|**2025-04-02**|**Interference with Gravitational Instability: Hot and Fuzzy Dark Matter**|Rayne Liu et.al.|[2504.01937v1](http://arxiv.org/abs/2504.01937v1)|null|

|**2025-04-02**|**Fermionic Averaged Circuit Eigenvalue Sampling**|Adrian Chapman et.al.|[2504.01936v1](http://arxiv.org/abs/2504.01936v1)|null|

|**2025-04-02**|**Critical Thinking: Which Kinds of Complexity Govern Optimal Reasoning Length?**|Celine Lee et.al.|[2504.01935v1](http://arxiv.org/abs/2504.01935v1)|null|

|**2025-04-02**|**ILLUME+: Illuminating Unified MLLM with Dual Visual Tokenization and Diffusion Refinement**|Runhui Huang et.al.|[2504.01934v2](http://arxiv.org/abs/2504.01934v2)|null|

|**2025-04-02**|**Hessian-aware Training for Enhancing DNNs Resilience to Parameter Corruptions**|Tahmid Hasan Prato et.al.|[2504.01933v1](http://arxiv.org/abs/2504.01933v1)|null|

|**2025-04-02**|**Semidefinite lower bounds for covering codes**|Dion Gijswijt et.al.|[2504.01932v1](http://arxiv.org/abs/2504.01932v1)|null|

|**2025-04-02**|**Review, Refine, Repeat: Understanding Iterative Decoding of AI Agents with Dynamic Evaluation and Selection**|Souradip Chakraborty et.al.|[2504.01931v1](http://arxiv.org/abs/2504.01931v1)|null|

## Contrastive Learning

### Contrastive Learning

|Publish Date|Title|Authors|PDF|Code|

| :---: | :---: | :---: | :---: | :---: |

|**2025-04-02**|**Learning from Streaming Video with Orthogonal Gradients**|Tengda Han et.al.|[2504.01961v1](http://arxiv.org/abs/2504.01961v1)|null|

|**2025-04-02**|**Diffusion-Guided Gaussian Splatting for Large-Scale Unconstrained 3D Reconstruction and Novel View Synthesis**|Niluthpol Chowdhury Mithun et.al.|[2504.01960v1](http://arxiv.org/abs/2504.01960v1)|null|

|**2025-04-02**|**Slot-Level Robotic Placement via Visual Imitation from Single Human Video**|Dandan Shan et.al.|[2504.01959v1](http://arxiv.org/abs/2504.01959v1)|null|

|**2025-04-02**|**Toward Real-world BEV Perception: Depth Uncertainty Estimation via Gaussian Splatting**|Shu-Wei Lu et.al.|[2504.01957v2](http://arxiv.org/abs/2504.01957v2)|null|

|**2025-04-02**|**Scene-Centric Unsupervised Panoptic Segmentation**|Oliver Hahn et.al.|[2504.01955v1](http://arxiv.org/abs/2504.01955v1)|null|

|**2025-04-02**|**Deep Representation Learning for Unsupervised Clustering of Myocardial Fiber Trajectories in Cardiac Diffusion Tensor Imaging**|Mohini Anand et.al.|[2504.01953v1](http://arxiv.org/abs/2504.01953v1)|null|

|**2025-04-02**|**Efficient Federated Learning Tiny Language Models for Mobile Network Feature Prediction**|Daniel Becking et.al.|[2504.01947v1](http://arxiv.org/abs/2504.01947v1)|null|

|**2025-04-02**|**OpenCodeReasoning: Advancing Data Distillation for Competitive Coding**|Wasi Uddin Ahmad et.al.|[2504.01943v1](http://arxiv.org/abs/2504.01943v1)|null|

|**2025-04-02**|**Strengthening Multi-Robot Systems for SAR: Co-Designing Robotics and Communication Towards 6G**|Juan Bravo-Arrabal et.al.|[2504.01940v1](http://arxiv.org/abs/2504.01940v1)|null|

|**2025-04-02**|**A Unified Approach to Analysis and Design of Denoising Markov Models**|Yinuo Ren et.al.|[2504.01938v1](http://arxiv.org/abs/2504.01938v1)|null|

|**2025-04-02**|**Fermionic Averaged Circuit Eigenvalue Sampling**|Adrian Chapman et.al.|[2504.01936v1](http://arxiv.org/abs/2504.01936v1)|null|

|**2025-04-02**|**ILLUME+: Illuminating Unified MLLM with Dual Visual Tokenization and Diffusion Refinement**|Runhui Huang et.al.|[2504.01934v2](http://arxiv.org/abs/2504.01934v2)|null|

|**2025-04-02**|**Hessian-aware Training for Enhancing DNNs Resilience to Parameter Corruptions**|Tahmid Hasan Prato et.al.|[2504.01933v1](http://arxiv.org/abs/2504.01933v1)|null|

|**2025-04-02**|**Is the Reversal Curse a Binding Problem? Uncovering Limitations of Transformers from a Basic Generalization Failure**|Boshi Wang et.al.|[2504.01928v1](http://arxiv.org/abs/2504.01928v1)|null|

|**2025-04-02**|**Gen-C: Populating Virtual Worlds with Generative Crowds**|Andreas Panayiotou et.al.|[2504.01924v1](http://arxiv.org/abs/2504.01924v1)|null|

|**2025-04-02**|**Client Selection in Federated Learning with Data Heterogeneity and Network Latencies**|Harsh Vardhan et.al.|[2504.01921v1](http://arxiv.org/abs/2504.01921v1)|null|

|**2025-04-02**|**FineLIP: Extending CLIP's Reach via Fine-Grained Alignment with Longer Text Inputs**|Mothilal Asokan et.al.|[2504.01916v1](http://arxiv.org/abs/2504.01916v1)|null|

|**2025-04-02**|**Overcoming Deceptiveness in Fitness Optimization with Unsupervised Quality-Diversity**|Lisa Coiffard et.al.|[2504.01915v1](http://arxiv.org/abs/2504.01915v1)|null|

|**2025-04-02**|**Representing Flow Fields with Divergence-Free Kernels for Reconstruction**|Xingyu Ni et.al.|[2504.01913v1](http://arxiv.org/abs/2504.01913v1)|null|

|**2025-04-02**|**Benchmarking Synthetic Tabular Data: A Multi-Dimensional Evaluation Framework**|Andrey Sidorenko et.al.|[2504.01908v1](http://arxiv.org/abs/2504.01908v1)|[link](https://github.com/mostly-ai/mostlyai-qa)|

|**2025-04-02**|**Accelerating IoV Intrusion Detection: Benchmarking GPU-Accelerated vs CPU-Based ML Libraries**|Furkan Çolhak et.al.|[2504.01905v2](http://arxiv.org/abs/2504.01905v2)|null|

|**2025-04-02**|**Graphically Speaking: Unmasking Abuse in Social Media with Conversation Insights**|Célia Nouri et.al.|[2504.01902v1](http://arxiv.org/abs/2504.01902v1)|null|

|**2025-04-02**|**Analysis of an Idealized Stochastic Polyak Method and its Application to Black-Box Model Distillation**|Robert M. Gower et.al.|[2504.01898v1](http://arxiv.org/abs/2504.01898v1)|null|

|**2025-04-02**|**Composition Design of Shape Memory Ceramics based on Gaussian Processes**|Ashutosh Pandey et.al.|[2504.01896v1](http://arxiv.org/abs/2504.01896v1)|null|

|**2025-04-02**|**Multi-fidelity Parameter Estimation Using Conditional Diffusion Models**|Caroline Tatsuoka et.al.|[2504.01894v1](http://arxiv.org/abs/2504.01894v1)|null|

|**2025-04-02**|**Is Temporal Prompting All We Need For Limited Labeled Action Recognition?**|Shreyank N Gowda et.al.|[2504.01890v1](http://arxiv.org/abs/2504.01890v1)|null|

|**2025-04-02**|**GMAI-VL-R1: Harnessing Reinforcement Learning for Multimodal Medical Reasoning**|Yanzhou Su et.al.|[2504.01886v1](http://arxiv.org/abs/2504.01886v1)|null|

|**2025-04-02**|**CoRAG: Collaborative Retrieval-Augmented Generation**|Aashiq Muhamed et.al.|[2504.01883v1](http://arxiv.org/abs/2504.01883v1)|null|

|**2025-04-02**|**CO-DEFEND: Continuous Decentralized Federated Learning for Secure DoH-Based Threat Detection**|Diego Cajaraville-Aboy et.al.|[2504.01882v1](http://arxiv.org/abs/2504.01882v1)|null|

|**2025-04-02**|**Effects of Dynamic Bonds on the Kinetic Pathways of Supramolecular Diblock Copolymers Disorder-Order Transition**|Xiangyu Zhang et.al.|[2504.01877v1](http://arxiv.org/abs/2504.01877v1)|null|

## Reinforcement Learning

### Reinforcement Learning

|Publish Date|Title|Authors|PDF|Code|

| :---: | :---: | :---: | :---: | :---: |

|**2025-04-02**|**OpenCodeReasoning: Advancing Data Distillation for Competitive Coding**|Wasi Uddin Ahmad et.al.|[2504.01943v1](http://arxiv.org/abs/2504.01943v1)|null|

|**2025-04-02**|**Overcoming Deceptiveness in Fitness Optimization with Unsupervised Quality-Diversity**|Lisa Coiffard et.al.|[2504.01915v1](http://arxiv.org/abs/2504.01915v1)|null|

|**2025-04-02**|**GMAI-VL-R1: Harnessing Reinforcement Learning for Multimodal Medical Reasoning**|Yanzhou Su et.al.|[2504.01886v1](http://arxiv.org/abs/2504.01886v1)|null|

|**2025-04-02**|**Interpreting Emergent Planning in Model-Free Reinforcement Learning**|Thomas Bush et.al.|[2504.01871v1](http://arxiv.org/abs/2504.01871v1)|null|

|**2025-04-02**|**Deciphering the Nature of Virgil: An Obscured AGN Lurking Within an Apparently Normal Lyman-α Emitter During Cosmic Reionization**|Pierluigi Rinaldi et.al.|[2504.01852v1](http://arxiv.org/abs/2504.01852v1)|null|

|**2025-04-02**|**Learning with Imperfect Models: When Multi-step Prediction Mitigates Compounding Error**|Anne Somalwar et.al.|[2504.01766v1](http://arxiv.org/abs/2504.01766v1)|null|

|**2025-04-02**|**Beyond Non-Expert Demonstrations: Outcome-Driven Action Constraint for Offline Reinforcement Learning**|Ke Jiang et.al.|[2504.01719v2](http://arxiv.org/abs/2504.01719v2)|null|

|**2025-04-02**|**ToM-RL: Reinforcement Learning Unlocks Theory of Mind in Small LLMs**|Yi-Long Lu et.al.|[2504.01698v1](http://arxiv.org/abs/2504.01698v1)|null|

|**2025-04-02**|**A Robust Model-Based Approach for Continuous-Time Policy Evaluation with Unknown Lévy Process Dynamics**|Qihao Ye et.al.|[2504.01482v1](http://arxiv.org/abs/2504.01482v1)|null|

|**2025-04-02**|**Probabilistic Curriculum Learning for Goal-Based Reinforcement Learning**|Llewyn Salt et.al.|[2504.01459v1](http://arxiv.org/abs/2504.01459v1)|null|

|**2025-04-02**|**Deep Graph Reinforcement Learning for UAV-Enabled Multi-User Secure Communications**|Xiao Tang et.al.|[2504.01446v1](http://arxiv.org/abs/2504.01446v1)|null|

|**2025-04-02**|**De Novo Molecular Design Enabled by Direct Preference Optimization and Curriculum Learning**|Junyu Hou et.al.|[2504.01389v1](http://arxiv.org/abs/2504.01389v1)|null|

|**2025-04-02**|**Inverse RL Scene Dynamics Learning for Nonlinear Predictive Control in Autonomous Vehicles**|Sorin Grigorescu et.al.|[2504.01336v1](http://arxiv.org/abs/2504.01336v1)|null|

|**2025-04-02**|**ThinkPrune: Pruning Long Chain-of-Thought of LLMs via Reinforcement Learning**|Bairu Hou et.al.|[2504.01296v1](http://arxiv.org/abs/2504.01296v1)|null|

|**2025-04-02**|**Scaling Test-Time Inference with Policy-Optimized, Dynamic Retrieval-Augmented Generation via KV Caching and Decoding**|Sakhinana Sagar Srinivas et.al.|[2504.01281v2](http://arxiv.org/abs/2504.01281v2)|null|

|**2025-04-01**|**Value Iteration for Learning Concurrently Executable Robotic Control Tasks**|Sheikh A. Tahmid et.al.|[2504.01174v1](http://arxiv.org/abs/2504.01174v1)|null|

|**2025-04-01**|**Extended Hybrid Zero Dynamics for Bipedal Walking of the Knee-less Robot SLIDER**|Rui Zong et.al.|[2504.01165v1](http://arxiv.org/abs/2504.01165v1)|null|

|**2025-04-01**|**MPCritic: A plug-and-play MPC architecture for reinforcement learning**|Nathan P. Lawrence et.al.|[2504.01086v1](http://arxiv.org/abs/2504.01086v1)|null|

|**2025-04-01**|**A Parametric Model for Near-Optimal Online Synthesis with Robust Reach-Avoid Guarantees**|Mario Gleirscher et.al.|[2504.01006v1](http://arxiv.org/abs/2504.01006v1)|null|

|**2025-04-01**|**Resource Allocation for RIS-Assisted CoMP-NOMA Networks using Reinforcement Learning**|Muhammad Umer et.al.|[2504.00975v1](http://arxiv.org/abs/2504.00975v1)|null|

|**2025-04-01**|**Grounding Multimodal LLMs to Embodied Agents that Ask for Help with Reinforcement Learning**|Ram Ramrakhya et.al.|[2504.00907v2](http://arxiv.org/abs/2504.00907v2)|null|

|**2025-04-01**|**How Difficulty-Aware Staged Reinforcement Learning Enhances LLMs' Reasoning Capabilities: A Preliminary Experimental Study**|Yunjie Ji et.al.|[2504.00829v1](http://arxiv.org/abs/2504.00829v1)|null|

|**2025-04-01**|**Reinforcement learning for robust dynamic metabolic control**|Sebastián Espinel-Ríos et.al.|[2504.00735v1](http://arxiv.org/abs/2504.00735v1)|null|

|**2025-04-01**|**Immersive Explainability: Visualizing Robot Navigation Decisions through XAI Semantic Scene Projections in Virtual Reality**|Jorge de Heuvel et.al.|[2504.00682v1](http://arxiv.org/abs/2504.00682v1)|null|

|**2025-04-01**|**Probabilistically safe and efficient model-based Reinforcement Learning**|Filippo Airaldi et.al.|[2504.00626v1](http://arxiv.org/abs/2504.00626v1)|null|

|**2025-04-01**|**Learning Bipedal Locomotion on Gear-Driven Humanoid Robot Using Foot-Mounted IMUs**|Sotaro Katayama et.al.|[2504.00614v1](http://arxiv.org/abs/2504.00614v1)|null|

|**2025-04-01**|**Mesoscale Eddy -- Internal Wave Coupling. III. The End of the Enstrophy Cascade and Maintenance of Gyre Scale Potential Vorticity Gradients**|Kurt L. Polzin et.al.|[2504.00486v1](http://arxiv.org/abs/2504.00486v1)|null|

|**2025-04-01**|**Efficient and Sustainable Task Offloading in UAV-Assisted MEC Systems via Meta Deep Reinforcement Learning**|Maryam Farajzadeh Dehkordi et.al.|[2504.00453v1](http://arxiv.org/abs/2504.00453v1)|null|

|**2025-04-01**|**Exposing the Ghost in the Transformer: Abnormal Detection for Large Language Models via Hidden State Forensics**|Shide Zhou et.al.|[2504.00446v1](http://arxiv.org/abs/2504.00446v1)|null|

|**2025-04-01**|**Hawkeye:Efficient Reasoning with Model Collaboration**|Jianshu She et.al.|[2504.00424v1](http://arxiv.org/abs/2504.00424v1)|null|

## Graph Neural Network

### Graph Neural Network

|Publish Date|Title|Authors|PDF|Code|

| :---: | :---: | :---: | :---: | :---: |

|**2025-04-02**|**Diffusion-Guided Gaussian Splatting for Large-Scale Unconstrained 3D Reconstruction and Novel View Synthesis**|Niluthpol Chowdhury Mithun et.al.|[2504.01960v1](http://arxiv.org/abs/2504.01960v1)|null|

|**2025-04-02**|**VideoScene: Distilling Video Diffusion Model to Generate 3D Scenes in One Step**|Hanyang Wang et.al.|[2504.01956v2](http://arxiv.org/abs/2504.01956v2)|null|

|**2025-04-02**|**Deep Representation Learning for Unsupervised Clustering of Myocardial Fiber Trajectories in Cardiac Diffusion Tensor Imaging**|Mohini Anand et.al.|[2504.01953v1](http://arxiv.org/abs/2504.01953v1)|null|

|**2025-04-02**|**Efficient Federated Learning Tiny Language Models for Mobile Network Feature Prediction**|Daniel Becking et.al.|[2504.01947v1](http://arxiv.org/abs/2504.01947v1)|null|

|**2025-04-02**|**Asynchronous Traffic Shaping and Redundancy: Avoiding Unbounded Latencies in In-Car Networks**|Teresa Lübeck et.al.|[2504.01946v1](http://arxiv.org/abs/2504.01946v1)|null|

|**2025-04-02**|**Graphon games and an idealized limit of large network games**|Motoki Otsuka et.al.|[2504.01944v1](http://arxiv.org/abs/2504.01944v1)|null|

|**2025-04-02**|**Strengthening Multi-Robot Systems for SAR: Co-Designing Robotics and Communication Towards 6G**|Juan Bravo-Arrabal et.al.|[2504.01940v1](http://arxiv.org/abs/2504.01940v1)|null|

|**2025-04-02**|**Hessian-aware Training for Enhancing DNNs Resilience to Parameter Corruptions**|Tahmid Hasan Prato et.al.|[2504.01933v1](http://arxiv.org/abs/2504.01933v1)|null|

|**2025-04-02**|**Equivariant Spherical CNNs for Accurate Fiber Orientation Distribution Estimation in Neonatal Diffusion MRI with Reduced Acquisition Time**|Haykel Snoussi et.al.|[2504.01925v1](http://arxiv.org/abs/2504.01925v1)|null|

|**2025-04-02**|**Gen-C: Populating Virtual Worlds with Generative Crowds**|Andreas Panayiotou et.al.|[2504.01924v1](http://arxiv.org/abs/2504.01924v1)|null|

|**2025-04-02**|**Client Selection in Federated Learning with Data Heterogeneity and Network Latencies**|Harsh Vardhan et.al.|[2504.01921v1](http://arxiv.org/abs/2504.01921v1)|null|

|**2025-04-02**|**Overcoming Deceptiveness in Fitness Optimization with Unsupervised Quality-Diversity**|Lisa Coiffard et.al.|[2504.01915v1](http://arxiv.org/abs/2504.01915v1)|null|

|**2025-04-02**|**Representing Flow Fields with Divergence-Free Kernels for Reconstruction**|Xingyu Ni et.al.|[2504.01913v1](http://arxiv.org/abs/2504.01913v1)|null|

|**2025-04-02**|**Accelerating IoV Intrusion Detection: Benchmarking GPU-Accelerated vs CPU-Based ML Libraries**|Furkan Çolhak et.al.|[2504.01905v2](http://arxiv.org/abs/2504.01905v2)|null|

|**2025-04-02**|**Graphically Speaking: Unmasking Abuse in Social Media with Conversation Insights**|Célia Nouri et.al.|[2504.01902v1](http://arxiv.org/abs/2504.01902v1)|null|

|**2025-04-02**|**Multi-stream Physics Hybrid Networks for solving Navier-Stokes equations**|Tatjana Protasevich et.al.|[2504.01891v1](http://arxiv.org/abs/2504.01891v1)|null|

|**2025-04-02**|**CO-DEFEND: Continuous Decentralized Federated Learning for Secure DoH-Based Threat Detection**|Diego Cajaraville-Aboy et.al.|[2504.01882v1](http://arxiv.org/abs/2504.01882v1)|null|

|**2025-04-02**|**Architect Your Landscape Approach (AYLA) for Optimizations in Deep Learning**|Ben Keslaki et.al.|[2504.01875v1](http://arxiv.org/abs/2504.01875v1)|null|

|**2025-04-02**|**Corner-Grasp: Multi-Action Grasp Detection and Active Gripper Adaptation for Grasping in Cluttered Environments**|Yeong Gwang Son et.al.|[2504.01861v1](http://arxiv.org/abs/2504.01861v1)|null|

|**2025-04-02**|**BOGausS: Better Optimized Gaussian Splatting**|Stéphane Pateux et.al.|[2504.01844v1](http://arxiv.org/abs/2504.01844v1)|null|

|**2025-04-02**|**Inference of hidden common driver dynamics by anisotropic self-organizing neural networks**|Zsigmond Benkő et.al.|[2504.01811v1](http://arxiv.org/abs/2504.01811v1)|null|

|**2025-04-02**|**Detector Response to Gravitational Wave Polarizations in Gravitational Quantum Field Theory**|Cong Xu et.al.|[2504.01809v1](http://arxiv.org/abs/2504.01809v1)|null|

|**2025-04-02**|**Coloring of graphs without long odd holes**|Ran Chen et.al.|[2504.01808v1](http://arxiv.org/abs/2504.01808v1)|null|

|**2025-04-02**|**Distributed Triangle Detection is Hard in Few Rounds**|Sepehr Assadi et.al.|[2504.01802v1](http://arxiv.org/abs/2504.01802v1)|null|

|**2025-04-02**|**A Novel Approach To Implementing Knowledge Distillation In Tsetlin Machines**|Calvin Kinateder et.al.|[2504.01798v1](http://arxiv.org/abs/2504.01798v1)|null|

|**2025-04-02**|**A combinatorial approach to the index of seaweed subalgebras of Kac--Moody algebras**|Oksana Yakimova et.al.|[2504.01791v1](http://arxiv.org/abs/2504.01791v1)|null|

|**2025-04-02**|**Leveraging Embedding Techniques in Multimodal Machine Learning for Mental Illness Assessment**|Abdelrahaman A. Hassan et.al.|[2504.01767v1](http://arxiv.org/abs/2504.01767v1)|null|

|**2025-04-02**|**KD$^{2}$M: An unifying framework for feature knowledge distillation**|Eduardo Fernandes Montesuma et.al.|[2504.01757v1](http://arxiv.org/abs/2504.01757v1)|null|

|**2025-04-02**|**Bridge the Gap between SNN and ANN for Image Restoration**|Xin Su et.al.|[2504.01755v1](http://arxiv.org/abs/2504.01755v1)|null|

|**2025-04-02**|**Stable Structure Learning with HC-Stable and Tabu-Stable Algorithms**|Neville K. Kitson et.al.|[2504.01740v1](http://arxiv.org/abs/2504.01740v1)|null|

## Robotics

### Robotics

|Publish Date|Title|Authors|PDF|Code|

| :---: | :---: | :---: | :---: | :---: |

|**2025-04-02**|**Slot-Level Robotic Placement via Visual Imitation from Single Human Video**|Dandan Shan et.al.|[2504.01959v1](http://arxiv.org/abs/2504.01959v1)|null|

|**2025-04-02**|**Strengthening Multi-Robot Systems for SAR: Co-Designing Robotics and Communication Towards 6G**|Juan Bravo-Arrabal et.al.|[2504.01940v1](http://arxiv.org/abs/2504.01940v1)|null|

|**2025-04-02**|**Overcoming Deceptiveness in Fitness Optimization with Unsupervised Quality-Diversity**|Lisa Coiffard et.al.|[2504.01915v1](http://arxiv.org/abs/2504.01915v1)|null|

|**2025-04-02**|**Ross3D: Reconstructive Visual Instruction Tuning with 3D-Awareness**|Haochen Wang et.al.|[2504.01901v1](http://arxiv.org/abs/2504.01901v1)|null|

|**2025-04-02**|**A novel gesture interaction control method for rehabilitation lower extremity exoskeleton**|Shuang Qiu et.al.|[2504.01888v1](http://arxiv.org/abs/2504.01888v1)|null|

|**2025-04-02**|**Corner-Grasp: Multi-Action Grasp Detection and Active Gripper Adaptation for Grasping in Cluttered Environments**|Yeong Gwang Son et.al.|[2504.01861v1](http://arxiv.org/abs/2504.01861v1)|null|

|**2025-04-02**|**Investigating the Variable Continuum Lags in PG 2130+099**|Jake A. Miller et.al.|[2504.01858v1](http://arxiv.org/abs/2504.01858v1)|null|

|**2025-04-02**|**Virtual Target Trajectory Prediction for Stochastic Targets**|Marc Schneider et.al.|[2504.01851v1](http://arxiv.org/abs/2504.01851v1)|null|

|**2025-04-02**|**Quattro: Transformer-Accelerated Iterative Linear Quadratic Regulator Framework for Fast Trajectory Optimization**|Yue Wang et.al.|[2504.01806v1](http://arxiv.org/abs/2504.01806v1)|null|

|**2025-04-02**|**Motility and rotation of multi-timescale microswimmers in linear background flows**|Eamonn A. Gaffney et.al.|[2504.01800v1](http://arxiv.org/abs/2504.01800v1)|null|

|**2025-04-02**|**SOLAQUA: SINTEF Ocean Large Aquaculture Robotics Dataset**|Sveinung Johan Ohrem et.al.|[2504.01790v1](http://arxiv.org/abs/2504.01790v1)|null|

|**2025-04-02**|**Beyond Non-Expert Demonstrations: Outcome-Driven Action Constraint for Offline Reinforcement Learning**|Ke Jiang et.al.|[2504.01719v2](http://arxiv.org/abs/2504.01719v2)|null|

|**2025-04-02**|**TransforMerger: Transformer-based Voice-Gesture Fusion for Robust Human-Robot Communication**|Petr Vanc et.al.|[2504.01708v1](http://arxiv.org/abs/2504.01708v1)|null|

|**2025-04-02**|**Reasoning LLMs for User-Aware Multimodal Conversational Agents**|Hamed Rahimi et.al.|[2504.01700v1](http://arxiv.org/abs/2504.01700v1)|null|

|**2025-04-02**|**Overlap-Aware Feature Learning for Robust Unsupervised Domain Adaptation for 3D Semantic Segmentation**|Junjie Chen et.al.|[2504.01668v1](http://arxiv.org/abs/2504.01668v1)|null|

|**2025-04-02**|**Proposition of Affordance-Driven Environment Recognition Framework Using Symbol Networks in Large Language Models**|Kazuma Arii et.al.|[2504.01644v1](http://arxiv.org/abs/2504.01644v1)|null|

|**2025-04-02**|**LLM-mediated Dynamic Plan Generation with a Multi-Agent Approach**|Reo Abe et.al.|[2504.01637v1](http://arxiv.org/abs/2504.01637v1)|null|

|**2025-04-02**|**Anticipating Degradation: A Predictive Approach to Fault Tolerance in Robot Swarms**|James O'Keeffe et.al.|[2504.01594v1](http://arxiv.org/abs/2504.01594v1)|null|

|**2025-04-02**|**Building Knowledge from Interactions: An LLM-Based Architecture for Adaptive Tutoring and Social Reasoning**|Luca Garello et.al.|[2504.01588v1](http://arxiv.org/abs/2504.01588v1)|null|

|**2025-04-02**|**LL-Localizer: A Life-Long Localization System based on Dynamic i-Octree**|Xinyi Li et.al.|[2504.01583v1](http://arxiv.org/abs/2504.01583v1)|null|

|**2025-04-02**|**8-DoFs Cable Driven Parallel Robots for Bimanual Teleportation**|Hung Hon Cheng et.al.|[2504.01554v1](http://arxiv.org/abs/2504.01554v1)|null|

|**2025-04-02**|**Grasping by Spiraling: Reproducing Elephant Movements with Rigid-Soft Robot Synergy**|Huishi Huang et.al.|[2504.01507v1](http://arxiv.org/abs/2504.01507v1)|null|

|**2025-04-02**|**Dynamic Initialization for LiDAR-inertial SLAM**|Jie Xu et.al.|[2504.01451v1](http://arxiv.org/abs/2504.01451v1)|null|

|**2025-04-02**|**DF-Calib: Targetless LiDAR-Camera Calibration via Depth Flow**|Shu Han et.al.|[2504.01416v1](http://arxiv.org/abs/2504.01416v1)|null|

|**2025-04-02**|**Pedestrian-Aware Motion Planning for Autonomous Driving in Complex Urban Scenarios**|Korbinian Moller et.al.|[2504.01409v1](http://arxiv.org/abs/2504.01409v1)|null|

|**2025-04-02**|**From Shadows to Safety: Occlusion Tracking and Risk Mitigation for Urban Autonomous Driving**|Korbinian Moller et.al.|[2504.01408v1](http://arxiv.org/abs/2504.01408v1)|null|

|**2025-04-02**|**Teaching Robots to Handle Nuclear Waste: A Teleoperation-Based Learning Approach<**|Joong-Ku Lee et.al.|[2504.01405v1](http://arxiv.org/abs/2504.01405v1)|null|

|**2025-04-02**|**Intuitive Human-Drone Collaborative Navigation in Unknown Environments through Mixed Reality**|Sanket A. Salunkhe et.al.|[2504.01350v1](http://arxiv.org/abs/2504.01350v1)|null|

|**2025-04-02**|**Inverse RL Scene Dynamics Learning for Nonlinear Predictive Control in Autonomous Vehicles**|Sorin Grigorescu et.al.|[2504.01336v1](http://arxiv.org/abs/2504.01336v1)|null|

|**2025-04-02**|**Bi-LAT: Bilateral Control-Based Imitation Learning via Natural Language and Action Chunking with Transformers**|Takumi Kobayashi et.al.|[2504.01301v1](http://arxiv.org/abs/2504.01301v1)|null|

### SFM

|Publish Date|Title|Authors|PDF|Code|

| :---: | :---: | :---: | :---: | :---: |

|**2025-04-02**|**Learning from Streaming Video with Orthogonal Gradients**|Tengda Han et.al.|[2504.01961v1](http://arxiv.org/abs/2504.01961v1)|null|

|**2025-04-02**|**Slot-Level Robotic Placement via Visual Imitation from Single Human Video**|Dandan Shan et.al.|[2504.01959v1](http://arxiv.org/abs/2504.01959v1)|null|

|**2025-04-02**|**Individual halo bias in models of $f(R)$ gravity**|Jorge Enrique García-Farieta et.al.|[2504.01958v1](http://arxiv.org/abs/2504.01958v1)|null|

|**2025-04-02**|**VideoScene: Distilling Video Diffusion Model to Generate 3D Scenes in One Step**|Hanyang Wang et.al.|[2504.01956v2](http://arxiv.org/abs/2504.01956v2)|null|

|**2025-04-02**|**Scene-Centric Unsupervised Panoptic Segmentation**|Oliver Hahn et.al.|[2504.01955v1](http://arxiv.org/abs/2504.01955v1)|null|

|**2025-04-02**|**Deep Representation Learning for Unsupervised Clustering of Myocardial Fiber Trajectories in Cardiac Diffusion Tensor Imaging**|Mohini Anand et.al.|[2504.01953v1](http://arxiv.org/abs/2504.01953v1)|null|

|**2025-04-02**|**The LLM Wears Prada: Analysing Gender Bias and Stereotypes through Online Shopping Data**|Massimiliano Luca et.al.|[2504.01951v1](http://arxiv.org/abs/2504.01951v1)|null|

|**2025-04-02**|**Nucleon scattering from lattice QCD**|Colin Morningstar et.al.|[2504.01950v1](http://arxiv.org/abs/2504.01950v1)|null|

|**2025-04-02**|**Comparison of Bayesian methods for extrapolation of treatment effects: a large scale simulation study**|Tristan Fauvel et.al.|[2504.01949v1](http://arxiv.org/abs/2504.01949v1)|null|

|**2025-04-02**|**PIMDAL: Mitigating the Memory Bottleneck in Data Analytics using a Real Processing-in-Memory System**|Manos Frouzakis et.al.|[2504.01948v1](http://arxiv.org/abs/2504.01948v1)|null|

|**2025-04-02**|**Asynchronous Traffic Shaping and Redundancy: Avoiding Unbounded Latencies in In-Car Networks**|Teresa Lübeck et.al.|[2504.01946v1](http://arxiv.org/abs/2504.01946v1)|null|

|**2025-04-02**|**Gluing moduli spaces of quantum toric stacks via secondary fan**|Antoine Boivin et.al.|[2504.01945v1](http://arxiv.org/abs/2504.01945v1)|null|

|**2025-04-02**|**OpenCodeReasoning: Advancing Data Distillation for Competitive Coding**|Wasi Uddin Ahmad et.al.|[2504.01943v1](http://arxiv.org/abs/2504.01943v1)|null|

|**2025-04-02**|**De Sitter entropy: on-shell versus off-shell**|Dmitrii Diakonov et.al.|[2504.01942v1](http://arxiv.org/abs/2504.01942v1)|null|

|**2025-04-02**|**Strengthening Multi-Robot Systems for SAR: Co-Designing Robotics and Communication Towards 6G**|Juan Bravo-Arrabal et.al.|[2504.01940v1](http://arxiv.org/abs/2504.01940v1)|null|

|**2025-04-02**|**Laboratory evaluation of a wearable instrumented headband for rotational head kinematics measurement**|Anu Tripathi et.al.|[2504.01939v1](http://arxiv.org/abs/2504.01939v1)|null|

|**2025-04-02**|**A Unified Approach to Analysis and Design of Denoising Markov Models**|Yinuo Ren et.al.|[2504.01938v1](http://arxiv.org/abs/2504.01938v1)|null|

|**2025-04-02**|**Fermionic Averaged Circuit Eigenvalue Sampling**|Adrian Chapman et.al.|[2504.01936v1](http://arxiv.org/abs/2504.01936v1)|null|

|**2025-04-02**|**Critical Thinking: Which Kinds of Complexity Govern Optimal Reasoning Length?**|Celine Lee et.al.|[2504.01935v1](http://arxiv.org/abs/2504.01935v1)|null|

|**2025-04-02**|**Review, Refine, Repeat: Understanding Iterative Decoding of AI Agents with Dynamic Evaluation and Selection**|Souradip Chakraborty et.al.|[2504.01931v1](http://arxiv.org/abs/2504.01931v1)|null|

|**2025-04-02**|**A thorough benchmark of automatic text classification: From traditional approaches to large language models**|Washington Cunha et.al.|[2504.01930v1](http://arxiv.org/abs/2504.01930v1)|null|

|**2025-04-02**|**Is the Reversal Curse a Binding Problem? Uncovering Limitations of Transformers from a Basic Generalization Failure**|Boshi Wang et.al.|[2504.01928v1](http://arxiv.org/abs/2504.01928v1)|null|

|**2025-04-02**|**Equivariant Spherical CNNs for Accurate Fiber Orientation Distribution Estimation in Neonatal Diffusion MRI with Reduced Acquisition Time**|Haykel Snoussi et.al.|[2504.01925v1](http://arxiv.org/abs/2504.01925v1)|null|

|**2025-04-02**|**Gen-C: Populating Virtual Worlds with Generative Crowds**|Andreas Panayiotou et.al.|[2504.01924v1](http://arxiv.org/abs/2504.01924v1)|null|

|**2025-04-02**|**Sliding Dynamics of Skyrmion Molecular Crystals**|J. C. Bellizotti Souza et.al.|[2504.01923v1](http://arxiv.org/abs/2504.01923v1)|null|

|**2025-04-02**|**Integrated sub-terahertz cavity electro-optic transduction**|Kevin K. S. Multani et.al.|[2504.01920v1](http://arxiv.org/abs/2504.01920v1)|null|

|**2025-04-02**|**Applying software engineering solutions to law management, Nigeria as a case study**|Chinonyerem Eleweke et.al.|[2504.01917v1](http://arxiv.org/abs/2504.01917v1)|null|

|**2025-04-02**|**Overcoming Deceptiveness in Fitness Optimization with Unsupervised Quality-Diversity**|Lisa Coiffard et.al.|[2504.01915v1](http://arxiv.org/abs/2504.01915v1)|null|

|**2025-04-02**|**Quantum-amplified global-phase spectroscopy on an optical clock transition**|Leon Zaporski et.al.|[2504.01914v1](http://arxiv.org/abs/2504.01914v1)|null|

|**2025-04-02**|**Representing Flow Fields with Divergence-Free Kernels for Reconstruction**|Xingyu Ni et.al.|[2504.01913v1](http://arxiv.org/abs/2504.01913v1)|null|

### SLAM

|Publish Date|Title|Authors|PDF|Code|

| :---: | :---: | :---: | :---: | :---: |

|**2025-04-02**|**Strengthening Multi-Robot Systems for SAR: Co-Designing Robotics and Communication Towards 6G**|Juan Bravo-Arrabal et.al.|[2504.01940v1](http://arxiv.org/abs/2504.01940v1)|null|

|**2025-04-02**|**Dynamic Initialization for LiDAR-inertial SLAM**|Jie Xu et.al.|[2504.01451v1](http://arxiv.org/abs/2504.01451v1)|null|

|**2025-03-31**|**SuperEvent: Cross-Modal Learning of Event-based Keypoint Detection**|Yannick Burkhardt et.al.|[2504.00139v1](http://arxiv.org/abs/2504.00139v1)|null|

|**2025-03-30**|**A Visual-Inertial Motion Prior SLAM for Dynamic Environments**|Weilong Sun et.al.|[2503.23429v1](http://arxiv.org/abs/2503.23429v1)|null|

|**2025-03-30**|**AnyCam: Learning to Recover Camera Poses and Intrinsics from Casual Videos**|Felix Wimbauer et.al.|[2503.23282v1](http://arxiv.org/abs/2503.23282v1)|null|

|**2025-03-27**|**HS-SLAM: Hybrid Representation with Structural Supervision for Improved Dense SLAM**|Ziren Gong et.al.|[2503.21778v1](http://arxiv.org/abs/2503.21778v1)|null|

|**2025-03-27**|**STAMICS: Splat, Track And Map with Integrated Consistency and Semantics for Dense RGB-D SLAM**|Yongxu Wang et.al.|[2503.21425v1](http://arxiv.org/abs/2503.21425v1)|null|

|**2025-03-25**|**First Results on UAV-aided User Localization Using ToA and OpenAirInterface in 5G NR**|Omid Esrafilian et.al.|[2503.19529v1](http://arxiv.org/abs/2503.19529v1)|null|

|**2025-03-25**|**MM-LINS: a Multi-Map LiDAR-Inertial System for Over-Degenerate Environments**|Yongxin Ma et.al.|[2503.19506v1](http://arxiv.org/abs/2503.19506v1)|[link](https://github.com/lian-yue0515/MM-LINS)|

|**2025-03-24**|**Cooperative Control of Multi-Quadrotors for Transporting Cable-Suspended Payloads: Obstacle-Aware Planning and Event-Based Nonlinear Model Predictive Control**|Tohid Kargar Tasooji et.al.|[2503.19135v1](http://arxiv.org/abs/2503.19135v1)|null|

|**2025-03-24**|**GI-SLAM: Gaussian-Inertial SLAM**|Xulang Liu et.al.|[2503.18275v1](http://arxiv.org/abs/2503.18275v1)|null|

|**2025-03-22**|**LightLoc: Learning Outdoor LiDAR Localization at Light Speed**|Wen Li et.al.|[2503.17814v1](http://arxiv.org/abs/2503.17814v1)|[link](https://github.com/liw95/lightloc)|

|**2025-03-21**|**Autonomous Exploration-Based Precise Mapping for Mobile Robots through Stepwise and Consistent Motions**|Muhua Zhang et.al.|[2503.17005v1](http://arxiv.org/abs/2503.17005v1)|null|

|**2025-03-20**|**4D Gaussian Splatting SLAM**|Yanyan Li et.al.|[2503.16710v1](http://arxiv.org/abs/2503.16710v1)|null|

|**2025-03-20**|**Speeding up design and making to reduce time-to-project and time-to-market: an AI-Enhanced approach in engineering education**|Giovanni Adorni et.al.|[2503.16307v1](http://arxiv.org/abs/2503.16307v1)|null|

|**2025-03-20**|**Loop Closure from Two Views: Revisiting PGO for Scalable Trajectory Estimation through Monocular Priors**|Tian Yi Lim et.al.|[2503.16275v1](http://arxiv.org/abs/2503.16275v1)|null|

|**2025-03-19**|**A Sigma Point-based Low Complexity Algorithm for Multipath-based SLAM in MIMO Systems**|Anna Masiero et.al.|[2503.15286v1](http://arxiv.org/abs/2503.15286v1)|null|

|**2025-03-19**|**ChatStitch: Visualizing Through Structures via Surround-View Unsupervised Deep Image Stitching with Collaborative LLM-Agents**|Hao Liang et.al.|[2503.14948v1](http://arxiv.org/abs/2503.14948v1)|null|

|**2025-03-18**|**3D Densification for Multi-Map Monocular VSLAM in Endoscopy**|X. Anadón et.al.|[2503.14346v1](http://arxiv.org/abs/2503.14346v1)|null|

|**2025-03-18**|**GeoFlow-SLAM: A Robust Tightly-Coupled RGBD-Inertial Fusion SLAM for Dynamic Legged Robotics**|Tingyang Xiao et.al.|[2503.14247v1](http://arxiv.org/abs/2503.14247v1)|[link](https://github.com/nsn-hello/geoflow-slam)|

|**2025-03-18**|**A-SCoRe: Attention-based Scene Coordinate Regression for wide-ranging scenarios**|Huy-Hoang Bui et.al.|[2503.13982v1](http://arxiv.org/abs/2503.13982v1)|[link](https://github.com/ais-lab/a-score)|

|**2025-03-17**|**Digital Beamforming Enhanced Radar Odometry**|Jingqi Jiang et.al.|[2503.13252v1](http://arxiv.org/abs/2503.13252v1)|null|

|**2025-03-17**|**Dynamic-Dark SLAM: RGB-Thermal Cooperative Robot Vision Strategy for Multi-Person Tracking in Both Well-Lit and Low-Light Scenes**|Tatsuro Sakai et.al.|[2503.12768v1](http://arxiv.org/abs/2503.12768v1)|null|

|**2025-03-16**|**KISS-SLAM: A Simple, Robust, and Accurate 3D LiDAR SLAM System With Enhanced Generalization Capabilities**|Tiziano Guadagnino et.al.|[2503.12660v1](http://arxiv.org/abs/2503.12660v1)|null|

|**2025-03-16**|**Deblur Gaussian Splatting SLAM**|Francesco Girlanda et.al.|[2503.12572v1](http://arxiv.org/abs/2503.12572v1)|null|

|**2025-03-16**|**M2UD: A Multi-model, Multi-scenario, Uneven-terrain Dataset for Ground Robot with Localization and Mapping Evaluation**|Yanpeng Jia et.al.|[2503.12387v1](http://arxiv.org/abs/2503.12387v1)|null|

|**2025-03-15**|**DynaGSLAM: Real-Time Gaussian-Splatting SLAM for Online Rendering, Tracking, Motion Predictions of Moving Objects in Dynamic Scenes**|Runfa Blark Li et.al.|[2503.11979v1](http://arxiv.org/abs/2503.11979v1)|null|

|**2025-03-14**|**AQUA-SLAM: Tightly-Coupled Underwater Acoustic-Visual-Inertial SLAM with Sensor Calibration**|Shida Xu et.al.|[2503.11420v1](http://arxiv.org/abs/2503.11420v1)|null|

|**2025-03-14**|**NF-SLAM: Effective, Normalizing Flow-supported Neural Field representations for object-level visual SLAM in automotive applications**|Li Cui et.al.|[2503.11199v1](http://arxiv.org/abs/2503.11199v1)|null|

|**2025-03-14**|**Leveraging Semantic Graphs for Efficient and Robust LiDAR SLAM**|Neng Wang et.al.|[2503.11145v1](http://arxiv.org/abs/2503.11145v1)|[link](https://github.com/nubot-nudt/sg-slam)|

### Visual Localization

|Publish Date|Title|Authors|PDF|Code|

| :---: | :---: | :---: | :---: | :---: |

|**2025-04-02**|**Diffusion-Guided Gaussian Splatting for Large-Scale Unconstrained 3D Reconstruction and Novel View Synthesis**|Niluthpol Chowdhury Mithun et.al.|[2504.01960v1](http://arxiv.org/abs/2504.01960v1)|null|

|**2025-04-02**|**A novel gesture interaction control method for rehabilitation lower extremity exoskeleton**|Shuang Qiu et.al.|[2504.01888v1](http://arxiv.org/abs/2504.01888v1)|null|

|**2025-04-02**|**Autonomous optical navigation for DESTINY+: Enhancing misalignment robustness in flyby observations with a rotating telescope**|Takayuki Hosonuma et.al.|[2504.01835v1](http://arxiv.org/abs/2504.01835v1)|null|

|**2025-04-02**|**SOLAQUA: SINTEF Ocean Large Aquaculture Robotics Dataset**|Sveinung Johan Ohrem et.al.|[2504.01790v1](http://arxiv.org/abs/2504.01790v1)|null|

|**2025-04-02**|**The Mini-SiTian Array: Evaluation Camera System**|Yu Zhang et.al.|[2504.01617v1](http://arxiv.org/abs/2504.01617v1)|null|

|**2025-04-02**|**The Mini-SiTian Array: Imaging Processing Pipeline**|Kai Xiao et.al.|[2504.01616v1](http://arxiv.org/abs/2504.01616v1)|null|

|**2025-04-02**|**Automatic Estimation of Pedestrian Gait Features using a single camera recording: Algorithm and Statistical Analysis for Gender Difference and Obstacle Interactions**|Kanika Jain et.al.|[2504.01600v1](http://arxiv.org/abs/2504.01600v1)|null|

|**2025-04-02**|**8-DoFs Cable Driven Parallel Robots for Bimanual Teleportation**|Hung Hon Cheng et.al.|[2504.01554v1](http://arxiv.org/abs/2504.01554v1)|null|

|**2025-04-02**|**Luminance-GS: Adapting 3D Gaussian Splatting to Challenging Lighting Conditions with View-Adaptive Curve Adjustment**|Ziteng Cui et.al.|[2504.01503v1](http://arxiv.org/abs/2504.01503v1)|null|

|**2025-04-02**|**DF-Calib: Targetless LiDAR-Camera Calibration via Depth Flow**|Shu Han et.al.|[2504.01416v1](http://arxiv.org/abs/2504.01416v1)|null|

|**2025-04-02**|**Direction-Aware Hybrid Representation Learning for 3D Hand Pose and Shape Estimation**|Shiyong Liu et.al.|[2504.01298v2](http://arxiv.org/abs/2504.01298v2)|null|

|**2025-04-02**|**A Retina-Inspired Pathway to Real-Time Motion Prediction inside Image Sensors for Extreme-Edge Intelligence**|Subhradip Chakraborty et.al.|[2504.01275v1](http://arxiv.org/abs/2504.01275v1)|null|

|**2025-04-02**|**ForestVO: Enhancing Visual Odometry in Forest Environments through ForestGlue**|Thomas Pritchard et.al.|[2504.01261v1](http://arxiv.org/abs/2504.01261v1)|null|

|**2025-04-01**|**rPPG-SysDiaGAN: Systolic-Diastolic Feature Localization in rPPG Using Generative Adversarial Network with Multi-Domain Discriminator**|Banafsheh Adami et.al.|[2504.01220v1](http://arxiv.org/abs/2504.01220v1)|null|

|**2025-04-01**|**Characterizing and exploiting cross-talk effect in SPAD arrays for two-photon interference**|Sergei Kulkov et.al.|[2504.01185v1](http://arxiv.org/abs/2504.01185v1)|null|

|**2025-04-01**|**RipVIS: Rip Currents Video Instance Segmentation Benchmark for Beach Monitoring and Safety**|Andrei Dumitriu et.al.|[2504.01128v2](http://arxiv.org/abs/2504.01128v2)|null|

|**2025-04-01**|**GeometryCrafter: Consistent Geometry Estimation for Open-world Videos with Diffusion Priors**|Tian-Xing Xu et.al.|[2504.01016v1](http://arxiv.org/abs/2504.01016v1)|null|

|**2025-04-01**|**WorldScore: A Unified Evaluation Benchmark for World Generation**|Haoyi Duan et.al.|[2504.00983v1](http://arxiv.org/abs/2504.00983v1)|null|

|**2025-04-01**|**NeuRadar: Neural Radiance Fields for Automotive Radar Point Clouds**|Mahan Rafidashti et.al.|[2504.00859v1](http://arxiv.org/abs/2504.00859v1)|null|

|**2025-04-01**|**Coca-Splat: Collaborative Optimization for Camera Parameters and 3D Gaussians**|Jiamin Wu et.al.|[2504.00639v1](http://arxiv.org/abs/2504.00639v1)|null|

|**2025-04-01**|**Robust LiDAR-Camera Calibration with 2D Gaussian Splatting**|Shuyi Zhou et.al.|[2504.00525v1](http://arxiv.org/abs/2504.00525v1)|null|

|**2025-04-01**|**Beyond Wide-Angle Images: Unsupervised Video Portrait Correction via Spatiotemporal Diffusion Adaptation**|Wenbo Nie et.al.|[2504.00401v1](http://arxiv.org/abs/2504.00401v1)|null|

|**2025-04-01**|**Scene4U: Hierarchical Layered 3D Scene Reconstruction from Single Panoramic Image for Your Immerse Exploration**|Zilong Huang et.al.|[2504.00387v1](http://arxiv.org/abs/2504.00387v1)|null|

|**2025-04-01**|**Spatiotemporal Attention Learning Framework for Event-Driven Object Recognition**|Tiantian Xie et.al.|[2504.00370v1](http://arxiv.org/abs/2504.00370v1)|null|

|**2025-03-31**|**RailGoerl24: Görlitz Rail Test Center CV Dataset 2024**|Rustam Tagiew et.al.|[2504.00204v1](http://arxiv.org/abs/2504.00204v1)|null|

|**2025-03-31**|**Self-Evolving Visual Concept Library using Vision-Language Critics**|Atharva Sehgal et.al.|[2504.00185v1](http://arxiv.org/abs/2504.00185v1)|null|

|**2025-03-31**|**Orbit, meteoroid size, and cosmic ray exposure history of the Aguas Zarcas CM2 breccia**|Peter Jenniskens et.al.|[2504.00183v1](http://arxiv.org/abs/2504.00183v1)|null|

|**2025-03-31**|**SuperEvent: Cross-Modal Learning of Event-based Keypoint Detection**|Yannick Burkhardt et.al.|[2504.00139v1](http://arxiv.org/abs/2504.00139v1)|null|

|**2025-03-31**|**Easi3R: Estimating Disentangled Motion from DUSt3R Without Training**|Xingyu Chen et.al.|[2503.24391v1](http://arxiv.org/abs/2503.24391v1)|[link](https://github.com/inception3d/easi3r)|

|**2025-03-31**|**UniOcc: A Unified Benchmark for Occupancy Forecasting and Prediction in Autonomous Driving**|Yuping Wang et.al.|[2503.24381v1](http://arxiv.org/abs/2503.24381v1)|[link](https://github.com/tasl-lab/uniocc)|

## Transformer

### Vision Transformer

|Publish Date|Title|Authors|PDF|Code|

| :---: | :---: | :---: | :---: | :---: |

|**2025-04-02**|**Learning from Streaming Video with Orthogonal Gradients**|Tengda Han et.al.|[2504.01961v1](http://arxiv.org/abs/2504.01961v1)|null|

|**2025-04-02**|**Diffusion-Guided Gaussian Splatting for Large-Scale Unconstrained 3D Reconstruction and Novel View Synthesis**|Niluthpol Chowdhury Mithun et.al.|[2504.01960v1](http://arxiv.org/abs/2504.01960v1)|null|

|**2025-04-02**|**Toward Real-world BEV Perception: Depth Uncertainty Estimation via Gaussian Splatting**|Shu-Wei Lu et.al.|[2504.01957v2](http://arxiv.org/abs/2504.01957v2)|null|

|**2025-04-02**|**VideoScene: Distilling Video Diffusion Model to Generate 3D Scenes in One Step**|Hanyang Wang et.al.|[2504.01956v2](http://arxiv.org/abs/2504.01956v2)|null|

|**2025-04-02**|**Scene-Centric Unsupervised Panoptic Segmentation**|Oliver Hahn et.al.|[2504.01955v1](http://arxiv.org/abs/2504.01955v1)|null|

|**2025-04-02**|**Towards Unified Referring Expression Segmentation Across Omni-Level Visual Target Granularities**|Jing Liu et.al.|[2504.01954v1](http://arxiv.org/abs/2504.01954v1)|null|

|**2025-04-02**|**Deep Representation Learning for Unsupervised Clustering of Myocardial Fiber Trajectories in Cardiac Diffusion Tensor Imaging**|Mohini Anand et.al.|[2504.01953v1](http://arxiv.org/abs/2504.01953v1)|null|

|**2025-04-02**|**Image Difference Grounding with Natural Language**|Wenxuan Wang et.al.|[2504.01952v1](http://arxiv.org/abs/2504.01952v1)|null|

|**2025-04-02**|**End-to-End Driving with Online Trajectory Evaluation via BEV World Model**|Yingyan Li et.al.|[2504.01941v1](http://arxiv.org/abs/2504.01941v1)|null|

|**2025-04-02**|**Laboratory evaluation of a wearable instrumented headband for rotational head kinematics measurement**|Anu Tripathi et.al.|[2504.01939v1](http://arxiv.org/abs/2504.01939v1)|null|

|**2025-04-02**|**Fermionic Averaged Circuit Eigenvalue Sampling**|Adrian Chapman et.al.|[2504.01936v1](http://arxiv.org/abs/2504.01936v1)|null|

|**2025-04-02**|**ILLUME+: Illuminating Unified MLLM with Dual Visual Tokenization and Diffusion Refinement**|Runhui Huang et.al.|[2504.01934v2](http://arxiv.org/abs/2504.01934v2)|null|

|**2025-04-02**|**A thorough benchmark of automatic text classification: From traditional approaches to large language models**|Washington Cunha et.al.|[2504.01930v1](http://arxiv.org/abs/2504.01930v1)|null|

|**2025-04-02**|**Is the Reversal Curse a Binding Problem? Uncovering Limitations of Transformers from a Basic Generalization Failure**|Boshi Wang et.al.|[2504.01928v1](http://arxiv.org/abs/2504.01928v1)|null|

|**2025-04-02**|**Equivariant Spherical CNNs for Accurate Fiber Orientation Distribution Estimation in Neonatal Diffusion MRI with Reduced Acquisition Time**|Haykel Snoussi et.al.|[2504.01925v1](http://arxiv.org/abs/2504.01925v1)|null|

|**2025-04-02**|**FineLIP: Extending CLIP's Reach via Fine-Grained Alignment with Longer Text Inputs**|Mothilal Asokan et.al.|[2504.01916v1](http://arxiv.org/abs/2504.01916v1)|null|

|**2025-04-02**|**Ross3D: Reconstructive Visual Instruction Tuning with 3D-Awareness**|Haochen Wang et.al.|[2504.01901v1](http://arxiv.org/abs/2504.01901v1)|null|

|**2025-04-02**|**Composition Design of Shape Memory Ceramics based on Gaussian Processes**|Ashutosh Pandey et.al.|[2504.01896v1](http://arxiv.org/abs/2504.01896v1)|null|

|**2025-04-02**|**Synchro-curvature description of γ-ray light curves and spectra of pulsars: concurrent fitting**|Daniel Íñiguez-Pascual et.al.|[2504.01892v1](http://arxiv.org/abs/2504.01892v1)|null|

|**2025-04-02**|**Is Temporal Prompting All We Need For Limited Labeled Action Recognition?**|Shreyank N Gowda et.al.|[2504.01890v1](http://arxiv.org/abs/2504.01890v1)|null|

|**2025-04-02**|**GMAI-VL-R1: Harnessing Reinforcement Learning for Multimodal Medical Reasoning**|Yanzhou Su et.al.|[2504.01886v1](http://arxiv.org/abs/2504.01886v1)|null|

|**2025-04-02**|**TransientTables: Evaluating LLMs' Reasoning on Temporally Evolving Semi-structured Tables**|Abhilash Shankarampeta et.al.|[2504.01879v1](http://arxiv.org/abs/2504.01879v1)|null|

|**2025-04-02**|**Architect Your Landscape Approach (AYLA) for Optimizations in Deep Learning**|Ben Keslaki et.al.|[2504.01875v1](http://arxiv.org/abs/2504.01875v1)|null|

|**2025-04-02**|**A Diffusion-Based Framework for Occluded Object Movement**|Zheng-Peng Duan et.al.|[2504.01873v1](http://arxiv.org/abs/2504.01873v1)|null|

|**2025-04-02**|**CoMatcher: Multi-View Collaborative Feature Matching**|Jintao Zhang et.al.|[2504.01872v1](http://arxiv.org/abs/2504.01872v1)|null|

|**2025-04-02**|**From Code Generation to Software Testing: AI Copilot with Context-Based RAG**|Yuchen Wang et.al.|[2504.01866v1](http://arxiv.org/abs/2504.01866v1)|null|

|**2025-04-02**|**A method to derive material-specific spin-bath model descriptions of materials displaying prevalent spin physics (for simulation on NISQ devices)**|Benedikt M. Schoenauer et.al.|[2504.01859v1](http://arxiv.org/abs/2504.01859v1)|null|

|**2025-04-02**|**An Approach to Technical AGI Safety and Security**|Rohin Shah et.al.|[2504.01849v1](http://arxiv.org/abs/2504.01849v1)|null|

|**2025-04-02**|**BOGausS: Better Optimized Gaussian Splatting**|Stéphane Pateux et.al.|[2504.01844v1](http://arxiv.org/abs/2504.01844v1)|null|

|**2025-04-02**|**Prompting Medical Vision-Language Models to Mitigate Diagnosis Bias by Generating Realistic Dermoscopic Images**|Nusrat Munia et.al.|[2504.01838v1](http://arxiv.org/abs/2504.01838v1)|null|

### Transformer

|Publish Date|Title|Authors|PDF|Code|

| :---: | :---: | :---: | :---: | :---: |

|**2025-04-02**|**Diffusion-Guided Gaussian Splatting for Large-Scale Unconstrained 3D Reconstruction and Novel View Synthesis**|Niluthpol Chowdhury Mithun et.al.|[2504.01960v1](http://arxiv.org/abs/2504.01960v1)|null|

|**2025-04-02**|**Toward Real-world BEV Perception: Depth Uncertainty Estimation via Gaussian Splatting**|Shu-Wei Lu et.al.|[2504.01957v2](http://arxiv.org/abs/2504.01957v2)|null|

|**2025-04-02**|**Deep Representation Learning for Unsupervised Clustering of Myocardial Fiber Trajectories in Cardiac Diffusion Tensor Imaging**|Mohini Anand et.al.|[2504.01953v1](http://arxiv.org/abs/2504.01953v1)|null|

|**2025-04-02**|**Laboratory evaluation of a wearable instrumented headband for rotational head kinematics measurement**|Anu Tripathi et.al.|[2504.01939v1](http://arxiv.org/abs/2504.01939v1)|null|

|**2025-04-02**|**Fermionic Averaged Circuit Eigenvalue Sampling**|Adrian Chapman et.al.|[2504.01936v1](http://arxiv.org/abs/2504.01936v1)|null|

|**2025-04-02**|**A thorough benchmark of automatic text classification: From traditional approaches to large language models**|Washington Cunha et.al.|[2504.01930v1](http://arxiv.org/abs/2504.01930v1)|null|

|**2025-04-02**|**Is the Reversal Curse a Binding Problem? Uncovering Limitations of Transformers from a Basic Generalization Failure**|Boshi Wang et.al.|[2504.01928v1](http://arxiv.org/abs/2504.01928v1)|null|

|**2025-04-02**|**Composition Design of Shape Memory Ceramics based on Gaussian Processes**|Ashutosh Pandey et.al.|[2504.01896v1](http://arxiv.org/abs/2504.01896v1)|null|

|**2025-04-02**|**Synchro-curvature description of γ-ray light curves and spectra of pulsars: concurrent fitting**|Daniel Íñiguez-Pascual et.al.|[2504.01892v1](http://arxiv.org/abs/2504.01892v1)|null|

|**2025-04-02**|**Architect Your Landscape Approach (AYLA) for Optimizations in Deep Learning**|Ben Keslaki et.al.|[2504.01875v1](http://arxiv.org/abs/2504.01875v1)|null|

|**2025-04-02**|**From Code Generation to Software Testing: AI Copilot with Context-Based RAG**|Yuchen Wang et.al.|[2504.01866v1](http://arxiv.org/abs/2504.01866v1)|null|

|**2025-04-02**|**A method to derive material-specific spin-bath model descriptions of materials displaying prevalent spin physics (for simulation on NISQ devices)**|Benedikt M. Schoenauer et.al.|[2504.01859v1](http://arxiv.org/abs/2504.01859v1)|null|

|**2025-04-02**|**An Approach to Technical AGI Safety and Security**|Rohin Shah et.al.|[2504.01849v1](http://arxiv.org/abs/2504.01849v1)|null|

|**2025-04-02**|**Prompting Medical Vision-Language Models to Mitigate Diagnosis Bias by Generating Realistic Dermoscopic Images**|Nusrat Munia et.al.|[2504.01838v1](http://arxiv.org/abs/2504.01838v1)|null|

|**2025-04-02**|**Quantum Meets SAR: A Novel Range-Doppler Algorithm for Next-Gen Earth Observation**|Khalil Al Salahat et.al.|[2504.01832v1](http://arxiv.org/abs/2504.01832v1)|null|

|**2025-04-02**|**Shape Theory via the Atiyah--Molino Reconstruction and Deformations**|Noémie C. Combe et.al.|[2504.01831v1](http://arxiv.org/abs/2504.01831v1)|null|

|**2025-04-02**|**Quattro: Transformer-Accelerated Iterative Linear Quadratic Regulator Framework for Fast Trajectory Optimization**|Yue Wang et.al.|[2504.01806v1](http://arxiv.org/abs/2504.01806v1)|null|

|**2025-04-02**|**UniViTAR: Unified Vision Transformer with Native Resolution**|Limeng Qiao et.al.|[2504.01792v1](http://arxiv.org/abs/2504.01792v1)|null|

|**2025-04-02**|**Triangular rogue clusters associated with multiple roots of Adler--Moser polynomials in integrable systems**|Bo Yang et.al.|[2504.01777v1](http://arxiv.org/abs/2504.01777v1)|null|

|**2025-04-02**|**Dual-stream Transformer-GCN Model with Contextualized Representations Learning for Monocular 3D Human Pose Estimation**|Mingrui Ye et.al.|[2504.01764v1](http://arxiv.org/abs/2504.01764v1)|null|

|**2025-04-02**|**Universal inverse Radon transforms: Inhomogeneity, angular restrictions and boundary**|I. V. Anikin et.al.|[2504.01744v1](http://arxiv.org/abs/2504.01744v1)|null|

|**2025-04-02**|**Understanding Cross-Model Perceptual Invariances Through Ensemble Metamers**|Lukas Boehm et.al.|[2504.01739v1](http://arxiv.org/abs/2504.01739v1)|null|

|**2025-04-02**|**DreamActor-M1: Holistic, Expressive and Robust Human Image Animation with Hybrid Guidance**|Yuxuan Luo et.al.|[2504.01724v2](http://arxiv.org/abs/2504.01724v2)|null|

|**2025-04-02**|**TransforMerger: Transformer-based Voice-Gesture Fusion for Robust Human-Robot Communication**|Petr Vanc et.al.|[2504.01708v1](http://arxiv.org/abs/2504.01708v1)|null|

|**2025-04-02**|**InfiniteICL: Breaking the Limit of Context Window Size via Long Short-term Memory Transformation**|Bowen Cao et.al.|[2504.01707v2](http://arxiv.org/abs/2504.01707v2)|null|

|**2025-04-02**|**Token Pruning in Audio Transformers: Optimizing Performance and Decoding Patch Importance**|Taehan Lee et.al.|[2504.01690v1](http://arxiv.org/abs/2504.01690v1)|null|

|**2025-04-02**|**Classification of the minimal-mass blowup solutions to the two dimensional focusing cubic nonlinear Schrödinger system**|Xing Cheng et.al.|[2504.01674v1](http://arxiv.org/abs/2504.01674v1)|null|

|**2025-04-02**|**Bridge 2D-3D: Uncertainty-aware Hierarchical Registration Network with Domain Alignment**|Zhixin Cheng et.al.|[2504.01641v1](http://arxiv.org/abs/2504.01641v1)|null|

|**2025-04-02**|**Benchmarking the Spatial Robustness of DNNs via Natural and Adversarial Localized Corruptions**|Giulia Marchiori Pietrosanti et.al.|[2504.01632v1](http://arxiv.org/abs/2504.01632v1)|null|

|**2025-04-02**|**On the performance of the Euler-Maruyama scheme for multidimensional SDEs with discontinuous drift coefficient**|Thomas Müller-Gronbach et.al.|[2504.01630v1](http://arxiv.org/abs/2504.01630v1)|null|

## Medical Application

### Medical Application

|Publish Date|Title|Authors|PDF|Code|

| :---: | :---: | :---: | :---: | :---: |

|**2025-04-02**|**Toward Real-world BEV Perception: Depth Uncertainty Estimation via Gaussian Splatting**|Shu-Wei Lu et.al.|[2504.01957v2](http://arxiv.org/abs/2504.01957v2)|null|

|**2025-04-02**|**Scene-Centric Unsupervised Panoptic Segmentation**|Oliver Hahn et.al.|[2504.01955v1](http://arxiv.org/abs/2504.01955v1)|null|

|**2025-04-02**|**Towards Unified Referring Expression Segmentation Across Omni-Level Visual Target Granularities**|Jing Liu et.al.|[2504.01954v1](http://arxiv.org/abs/2504.01954v1)|null|

|**2025-04-02**|**Deep Representation Learning for Unsupervised Clustering of Myocardial Fiber Trajectories in Cardiac Diffusion Tensor Imaging**|Mohini Anand et.al.|[2504.01953v1](http://arxiv.org/abs/2504.01953v1)|null|

|**2025-04-02**|**Image Difference Grounding with Natural Language**|Wenxuan Wang et.al.|[2504.01952v1](http://arxiv.org/abs/2504.01952v1)|null|

|**2025-04-02**|**Nucleon scattering from lattice QCD**|Colin Morningstar et.al.|[2504.01950v1](http://arxiv.org/abs/2504.01950v1)|null|

|**2025-04-02**|**PIMDAL: Mitigating the Memory Bottleneck in Data Analytics using a Real Processing-in-Memory System**|Manos Frouzakis et.al.|[2504.01948v1](http://arxiv.org/abs/2504.01948v1)|null|

|**2025-04-02**|**Efficient Federated Learning Tiny Language Models for Mobile Network Feature Prediction**|Daniel Becking et.al.|[2504.01947v1](http://arxiv.org/abs/2504.01947v1)|null|

|**2025-04-02**|**End-to-End Driving with Online Trajectory Evaluation via BEV World Model**|Yingyan Li et.al.|[2504.01941v1](http://arxiv.org/abs/2504.01941v1)|null|

|**2025-04-02**|**Laboratory evaluation of a wearable instrumented headband for rotational head kinematics measurement**|Anu Tripathi et.al.|[2504.01939v1](http://arxiv.org/abs/2504.01939v1)|null|

|**2025-04-02**|**A Unified Approach to Analysis and Design of Denoising Markov Models**|Yinuo Ren et.al.|[2504.01938v1](http://arxiv.org/abs/2504.01938v1)|null|

|**2025-04-02**|**ILLUME+: Illuminating Unified MLLM with Dual Visual Tokenization and Diffusion Refinement**|Runhui Huang et.al.|[2504.01934v2](http://arxiv.org/abs/2504.01934v2)|null|

|**2025-04-02**|**Source Coding for a Wiener Process**|Sahan Liyanaarachchi et.al.|[2504.01929v1](http://arxiv.org/abs/2504.01929v1)|null|

|**2025-04-02**|**Equivariant Spherical CNNs for Accurate Fiber Orientation Distribution Estimation in Neonatal Diffusion MRI with Reduced Acquisition Time**|Haykel Snoussi et.al.|[2504.01925v1](http://arxiv.org/abs/2504.01925v1)|null|

|**2025-04-02**|**Is Less Really More? Fake News Detection with Limited Information**|Zhaoyang Cao et.al.|[2504.01922v1](http://arxiv.org/abs/2504.01922v1)|[link](https://github.com/kappakant/SLIM)|

|**2025-04-02**|**Applying software engineering solutions to law management, Nigeria as a case study**|Chinonyerem Eleweke et.al.|[2504.01917v1](http://arxiv.org/abs/2504.01917v1)|null|

|**2025-04-02**|**FineLIP: Extending CLIP's Reach via Fine-Grained Alignment with Longer Text Inputs**|Mothilal Asokan et.al.|[2504.01916v1](http://arxiv.org/abs/2504.01916v1)|null|

|**2025-04-02**|**Accelerating IoV Intrusion Detection: Benchmarking GPU-Accelerated vs CPU-Based ML Libraries**|Furkan Çolhak et.al.|[2504.01905v2](http://arxiv.org/abs/2504.01905v2)|null|

|**2025-04-02**|**Graphically Speaking: Unmasking Abuse in Social Media with Conversation Insights**|Célia Nouri et.al.|[2504.01902v1](http://arxiv.org/abs/2504.01902v1)|null|

|**2025-04-02**|**Ross3D: Reconstructive Visual Instruction Tuning with 3D-Awareness**|Haochen Wang et.al.|[2504.01901v1](http://arxiv.org/abs/2504.01901v1)|null|

|**2025-04-02**|**Composition Design of Shape Memory Ceramics based on Gaussian Processes**|Ashutosh Pandey et.al.|[2504.01896v1](http://arxiv.org/abs/2504.01896v1)|null|

|**2025-04-02**|**A minimal Pati-Salam theory: from cosmic defects to gravitational waves and colliders**|Goran Senjanović et.al.|[2504.01893v1](http://arxiv.org/abs/2504.01893v1)|null|

|**2025-04-02**|**Multi-stream Physics Hybrid Networks for solving Navier-Stokes equations**|Tatjana Protasevich et.al.|[2504.01891v1](http://arxiv.org/abs/2504.01891v1)|null|

|**2025-04-02**|**Dual mechanism of Anti-Seizure Medications in controlling seizure activity**|Guillermo M. Besne et.al.|[2504.01887v1](http://arxiv.org/abs/2504.01887v1)|null|

|**2025-04-02**|**GMAI-VL-R1: Harnessing Reinforcement Learning for Multimodal Medical Reasoning**|Yanzhou Su et.al.|[2504.01886v1](http://arxiv.org/abs/2504.01886v1)|null|

|**2025-04-02**|**CO-DEFEND: Continuous Decentralized Federated Learning for Secure DoH-Based Threat Detection**|Diego Cajaraville-Aboy et.al.|[2504.01882v1](http://arxiv.org/abs/2504.01882v1)|null|

|**2025-04-02**|**Effects of Dynamic Bonds on the Kinetic Pathways of Supramolecular Diblock Copolymers Disorder-Order Transition**|Xiangyu Zhang et.al.|[2504.01877v1](http://arxiv.org/abs/2504.01877v1)|null|

|**2025-04-02**|**A Diffusion-Based Framework for Occluded Object Movement**|Zheng-Peng Duan et.al.|[2504.01873v1](http://arxiv.org/abs/2504.01873v1)|null|

|**2025-04-02**|**CoMatcher: Multi-View Collaborative Feature Matching**|Jintao Zhang et.al.|[2504.01872v1](http://arxiv.org/abs/2504.01872v1)|null|

|**2025-04-02**|**Buggin: Automatic intrinsic bugs classification model using NLP and ML**|Pragya Bhandari et.al.|[2504.01869v1](http://arxiv.org/abs/2504.01869v1)|null|

### Medical Image Analysis

|Publish Date|Title|Authors|PDF|Code|

| :---: | :---: | :---: | :---: | :---: |

|**2025-04-02**|**Toward Real-world BEV Perception: Depth Uncertainty Estimation via Gaussian Splatting**|Shu-Wei Lu et.al.|[2504.01957v2](http://arxiv.org/abs/2504.01957v2)|null|

|**2025-04-02**|**Scene-Centric Unsupervised Panoptic Segmentation**|Oliver Hahn et.al.|[2504.01955v1](http://arxiv.org/abs/2504.01955v1)|null|

|**2025-04-02**|**Towards Unified Referring Expression Segmentation Across Omni-Level Visual Target Granularities**|Jing Liu et.al.|[2504.01954v1](http://arxiv.org/abs/2504.01954v1)|null|

|**2025-04-02**|**Deep Representation Learning for Unsupervised Clustering of Myocardial Fiber Trajectories in Cardiac Diffusion Tensor Imaging**|Mohini Anand et.al.|[2504.01953v1](http://arxiv.org/abs/2504.01953v1)|null|

|**2025-04-02**|**Image Difference Grounding with Natural Language**|Wenxuan Wang et.al.|[2504.01952v1](http://arxiv.org/abs/2504.01952v1)|null|

|**2025-04-02**|**Nucleon scattering from lattice QCD**|Colin Morningstar et.al.|[2504.01950v1](http://arxiv.org/abs/2504.01950v1)|null|

|**2025-04-02**|**PIMDAL: Mitigating the Memory Bottleneck in Data Analytics using a Real Processing-in-Memory System**|Manos Frouzakis et.al.|[2504.01948v1](http://arxiv.org/abs/2504.01948v1)|null|

|**2025-04-02**|**Efficient Federated Learning Tiny Language Models for Mobile Network Feature Prediction**|Daniel Becking et.al.|[2504.01947v1](http://arxiv.org/abs/2504.01947v1)|null|

|**2025-04-02**|**End-to-End Driving with Online Trajectory Evaluation via BEV World Model**|Yingyan Li et.al.|[2504.01941v1](http://arxiv.org/abs/2504.01941v1)|null|

|**2025-04-02**|**Laboratory evaluation of a wearable instrumented headband for rotational head kinematics measurement**|Anu Tripathi et.al.|[2504.01939v1](http://arxiv.org/abs/2504.01939v1)|null|

|**2025-04-02**|**A Unified Approach to Analysis and Design of Denoising Markov Models**|Yinuo Ren et.al.|[2504.01938v1](http://arxiv.org/abs/2504.01938v1)|null|

|**2025-04-02**|**ILLUME+: Illuminating Unified MLLM with Dual Visual Tokenization and Diffusion Refinement**|Runhui Huang et.al.|[2504.01934v2](http://arxiv.org/abs/2504.01934v2)|null|

|**2025-04-02**|**Source Coding for a Wiener Process**|Sahan Liyanaarachchi et.al.|[2504.01929v1](http://arxiv.org/abs/2504.01929v1)|null|

|**2025-04-02**|**Equivariant Spherical CNNs for Accurate Fiber Orientation Distribution Estimation in Neonatal Diffusion MRI with Reduced Acquisition Time**|Haykel Snoussi et.al.|[2504.01925v1](http://arxiv.org/abs/2504.01925v1)|null|

|**2025-04-02**|**Is Less Really More? Fake News Detection with Limited Information**|Zhaoyang Cao et.al.|[2504.01922v1](http://arxiv.org/abs/2504.01922v1)|[link](https://github.com/kappakant/SLIM)|

|**2025-04-02**|**Applying software engineering solutions to law management, Nigeria as a case study**|Chinonyerem Eleweke et.al.|[2504.01917v1](http://arxiv.org/abs/2504.01917v1)|null|

|**2025-04-02**|**FineLIP: Extending CLIP's Reach via Fine-Grained Alignment with Longer Text Inputs**|Mothilal Asokan et.al.|[2504.01916v1](http://arxiv.org/abs/2504.01916v1)|null|

|**2025-04-02**|**Accelerating IoV Intrusion Detection: Benchmarking GPU-Accelerated vs CPU-Based ML Libraries**|Furkan Çolhak et.al.|[2504.01905v2](http://arxiv.org/abs/2504.01905v2)|null|

|**2025-04-02**|**Graphically Speaking: Unmasking Abuse in Social Media with Conversation Insights**|Célia Nouri et.al.|[2504.01902v1](http://arxiv.org/abs/2504.01902v1)|null|

|**2025-04-02**|**Ross3D: Reconstructive Visual Instruction Tuning with 3D-Awareness**|Haochen Wang et.al.|[2504.01901v1](http://arxiv.org/abs/2504.01901v1)|null|

|**2025-04-02**|**Composition Design of Shape Memory Ceramics based on Gaussian Processes**|Ashutosh Pandey et.al.|[2504.01896v1](http://arxiv.org/abs/2504.01896v1)|null|

|**2025-04-02**|**A minimal Pati-Salam theory: from cosmic defects to gravitational waves and colliders**|Goran Senjanović et.al.|[2504.01893v1](http://arxiv.org/abs/2504.01893v1)|null|

|**2025-04-02**|**Multi-stream Physics Hybrid Networks for solving Navier-Stokes equations**|Tatjana Protasevich et.al.|[2504.01891v1](http://arxiv.org/abs/2504.01891v1)|null|

|**2025-04-02**|**Dual mechanism of Anti-Seizure Medications in controlling seizure activity**|Guillermo M. Besne et.al.|[2504.01887v1](http://arxiv.org/abs/2504.01887v1)|null|

|**2025-04-02**|**GMAI-VL-R1: Harnessing Reinforcement Learning for Multimodal Medical Reasoning**|Yanzhou Su et.al.|[2504.01886v1](http://arxiv.org/abs/2504.01886v1)|null|

|**2025-04-02**|**CO-DEFEND: Continuous Decentralized Federated Learning for Secure DoH-Based Threat Detection**|Diego Cajaraville-Aboy et.al.|[2504.01882v1](http://arxiv.org/abs/2504.01882v1)|null|

|**2025-04-02**|**Effects of Dynamic Bonds on the Kinetic Pathways of Supramolecular Diblock Copolymers Disorder-Order Transition**|Xiangyu Zhang et.al.|[2504.01877v1](http://arxiv.org/abs/2504.01877v1)|null|

|**2025-04-02**|**A Diffusion-Based Framework for Occluded Object Movement**|Zheng-Peng Duan et.al.|[2504.01873v1](http://arxiv.org/abs/2504.01873v1)|null|

|**2025-04-02**|**CoMatcher: Multi-View Collaborative Feature Matching**|Jintao Zhang et.al.|[2504.01872v1](http://arxiv.org/abs/2504.01872v1)|null|

|**2025-04-02**|**Buggin: Automatic intrinsic bugs classification model using NLP and ML**|Pragya Bhandari et.al.|[2504.01869v1](http://arxiv.org/abs/2504.01869v1)|null|

### Medical Multi-modal

|Publish Date|Title|Authors|PDF|Code|

| :---: | :---: | :---: | :---: | :---: |

|**2025-04-02**|**Learning from Streaming Video with Orthogonal Gradients**|Tengda Han et.al.|[2504.01961v1](http://arxiv.org/abs/2504.01961v1)|null|

|**2025-04-02**|**Diffusion-Guided Gaussian Splatting for Large-Scale Unconstrained 3D Reconstruction and Novel View Synthesis**|Niluthpol Chowdhury Mithun et.al.|[2504.01960v1](http://arxiv.org/abs/2504.01960v1)|null|

|**2025-04-02**|**Towards Unified Referring Expression Segmentation Across Omni-Level Visual Target Granularities**|Jing Liu et.al.|[2504.01954v1](http://arxiv.org/abs/2504.01954v1)|null|

|**2025-04-02**|**Image Difference Grounding with Natural Language**|Wenxuan Wang et.al.|[2504.01952v1](http://arxiv.org/abs/2504.01952v1)|null|

|**2025-04-02**|**Strengthening Multi-Robot Systems for SAR: Co-Designing Robotics and Communication Towards 6G**|Juan Bravo-Arrabal et.al.|[2504.01940v1](http://arxiv.org/abs/2504.01940v1)|null|

|**2025-04-02**|**Review, Refine, Repeat: Understanding Iterative Decoding of AI Agents with Dynamic Evaluation and Selection**|Souradip Chakraborty et.al.|[2504.01931v1](http://arxiv.org/abs/2504.01931v1)|null|

|**2025-04-02**|**Equivariant Spherical CNNs for Accurate Fiber Orientation Distribution Estimation in Neonatal Diffusion MRI with Reduced Acquisition Time**|Haykel Snoussi et.al.|[2504.01925v1](http://arxiv.org/abs/2504.01925v1)|null|

|**2025-04-02**|**Is Less Really More? Fake News Detection with Limited Information**|Zhaoyang Cao et.al.|[2504.01922v1](http://arxiv.org/abs/2504.01922v1)|[link](https://github.com/kappakant/SLIM)|

|**2025-04-02**|**FineLIP: Extending CLIP's Reach via Fine-Grained Alignment with Longer Text Inputs**|Mothilal Asokan et.al.|[2504.01916v1](http://arxiv.org/abs/2504.01916v1)|null|

|**2025-04-02**|**Benchmarking Synthetic Tabular Data: A Multi-Dimensional Evaluation Framework**|Andrey Sidorenko et.al.|[2504.01908v1](http://arxiv.org/abs/2504.01908v1)|[link](https://github.com/mostly-ai/mostlyai-qa)|

|**2025-04-02**|**Multi-fidelity Parameter Estimation Using Conditional Diffusion Models**|Caroline Tatsuoka et.al.|[2504.01894v1](http://arxiv.org/abs/2504.01894v1)|null|

|**2025-04-02**|**Multi-stream Physics Hybrid Networks for solving Navier-Stokes equations**|Tatjana Protasevich et.al.|[2504.01891v1](http://arxiv.org/abs/2504.01891v1)|null|

|**2025-04-02**|**Dual mechanism of Anti-Seizure Medications in controlling seizure activity**|Guillermo M. Besne et.al.|[2504.01887v1](http://arxiv.org/abs/2504.01887v1)|null|

|**2025-04-02**|**GMAI-VL-R1: Harnessing Reinforcement Learning for Multimodal Medical Reasoning**|Yanzhou Su et.al.|[2504.01886v1](http://arxiv.org/abs/2504.01886v1)|null|

|**2025-04-02**|**CoMatcher: Multi-View Collaborative Feature Matching**|Jintao Zhang et.al.|[2504.01872v1](http://arxiv.org/abs/2504.01872v1)|null|

|**2025-04-02**|**Corner-Grasp: Multi-Action Grasp Detection and Active Gripper Adaptation for Grasping in Cluttered Environments**|Yeong Gwang Son et.al.|[2504.01861v1](http://arxiv.org/abs/2504.01861v1)|null|

|**2025-04-02**|**A method to derive material-specific spin-bath model descriptions of materials displaying prevalent spin physics (for simulation on NISQ devices)**|Benedikt M. Schoenauer et.al.|[2504.01859v1](http://arxiv.org/abs/2504.01859v1)|null|

|**2025-04-02**|**Lower Bounds for Leader Election and Collective Coin Flipping, Revisited**|Eshan Chattopadhyay et.al.|[2504.01856v1](http://arxiv.org/abs/2504.01856v1)|null|

|**2025-04-02**|**Deciphering the Nature of Virgil: An Obscured AGN Lurking Within an Apparently Normal Lyman-α Emitter During Cosmic Reionization**|Pierluigi Rinaldi et.al.|[2504.01852v1](http://arxiv.org/abs/2504.01852v1)|null|

|**2025-04-02**|**Prompting Medical Vision-Language Models to Mitigate Diagnosis Bias by Generating Realistic Dermoscopic Images**|Nusrat Munia et.al.|[2504.01838v1](http://arxiv.org/abs/2504.01838v1)|null|

|**2025-04-02**|**Track and Trace: Automatically Uncovering Cross-chain Transactions in the Multi-blockchain Ecosystems**|Dan Lin et.al.|[2504.01822v1](http://arxiv.org/abs/2504.01822v1)|null|

|**2025-04-02**|**Efficient Constant-Space Multi-Vector Retrieval**|Sean MacAvaney et.al.|[2504.01818v1](http://arxiv.org/abs/2504.01818v1)|null|

|**2025-04-02**|**Multi-actuator lens systems for turbulence correction in free-space optical communications**|Matteo Schiavon et.al.|[2504.01817v1](http://arxiv.org/abs/2504.01817v1)|null|

|**2025-04-02**|**Detector Response to Gravitational Wave Polarizations in Gravitational Quantum Field Theory**|Cong Xu et.al.|[2504.01809v1](http://arxiv.org/abs/2504.01809v1)|null|

|**2025-04-02**|**Spatial-R1: Enhancing MLLMs in Video Spatial Reasoning**|Kun Ouyang et.al.|[2504.01805v1](http://arxiv.org/abs/2504.01805v1)|null|

|**2025-04-02**|**Distributed Triangle Detection is Hard in Few Rounds**|Sepehr Assadi et.al.|[2504.01802v1](http://arxiv.org/abs/2504.01802v1)|null|

|**2025-04-02**|**Motility and rotation of multi-timescale microswimmers in linear background flows**|Eamonn A. Gaffney et.al.|[2504.01800v1](http://arxiv.org/abs/2504.01800v1)|null|

|**2025-04-02**|**UniViTAR: Unified Vision Transformer with Native Resolution**|Limeng Qiao et.al.|[2504.01792v1](http://arxiv.org/abs/2504.01792v1)|null|

|**2025-04-02**|**OpenThaiGPT 1.6 and R1: Thai-Centric Open Source and Reasoning Large Language Models**|Sumeth Yuenyong et.al.|[2504.01789v1](http://arxiv.org/abs/2504.01789v1)|null|

|**2025-04-02**|**Optimized Schwarz method for the Stokes-Darcy problem with generalized interface conditions**|Paula Strohbeck et.al.|[2504.01784v1](http://arxiv.org/abs/2504.01784v1)|null|

## Large-Language Model

### Large-Language Model

|Publish Date|Title|Authors|PDF|Code|

| :---: | :---: | :---: | :---: | :---: |

|**2025-04-02**|**Learning from Streaming Video with Orthogonal Gradients**|Tengda Han et.al.|[2504.01961v1](http://arxiv.org/abs/2504.01961v1)|null|

|**2025-04-02**|**Diffusion-Guided Gaussian Splatting for Large-Scale Unconstrained 3D Reconstruction and Novel View Synthesis**|Niluthpol Chowdhury Mithun et.al.|[2504.01960v1](http://arxiv.org/abs/2504.01960v1)|null|

|**2025-04-02**|**Slot-Level Robotic Placement via Visual Imitation from Single Human Video**|Dandan Shan et.al.|[2504.01959v1](http://arxiv.org/abs/2504.01959v1)|null|

|**2025-04-02**|**Individual halo bias in models of $f(R)$ gravity**|Jorge Enrique García-Farieta et.al.|[2504.01958v1](http://arxiv.org/abs/2504.01958v1)|null|

|**2025-04-02**|**Toward Real-world BEV Perception: Depth Uncertainty Estimation via Gaussian Splatting**|Shu-Wei Lu et.al.|[2504.01957v2](http://arxiv.org/abs/2504.01957v2)|null|

|**2025-04-02**|**VideoScene: Distilling Video Diffusion Model to Generate 3D Scenes in One Step**|Hanyang Wang et.al.|[2504.01956v2](http://arxiv.org/abs/2504.01956v2)|null|

|**2025-04-02**|**Towards Unified Referring Expression Segmentation Across Omni-Level Visual Target Granularities**|Jing Liu et.al.|[2504.01954v1](http://arxiv.org/abs/2504.01954v1)|null|

|**2025-04-02**|**Deep Representation Learning for Unsupervised Clustering of Myocardial Fiber Trajectories in Cardiac Diffusion Tensor Imaging**|Mohini Anand et.al.|[2504.01953v1](http://arxiv.org/abs/2504.01953v1)|null|

|**2025-04-02**|**Image Difference Grounding with Natural Language**|Wenxuan Wang et.al.|[2504.01952v1](http://arxiv.org/abs/2504.01952v1)|null|

|**2025-04-02**|**The LLM Wears Prada: Analysing Gender Bias and Stereotypes through Online Shopping Data**|Massimiliano Luca et.al.|[2504.01951v1](http://arxiv.org/abs/2504.01951v1)|null|

|**2025-04-02**|**Comparison of Bayesian methods for extrapolation of treatment effects: a large scale simulation study**|Tristan Fauvel et.al.|[2504.01949v1](http://arxiv.org/abs/2504.01949v1)|null|

|**2025-04-02**|**Efficient Federated Learning Tiny Language Models for Mobile Network Feature Prediction**|Daniel Becking et.al.|[2504.01947v1](http://arxiv.org/abs/2504.01947v1)|null|

|**2025-04-02**|**Asynchronous Traffic Shaping and Redundancy: Avoiding Unbounded Latencies in In-Car Networks**|Teresa Lübeck et.al.|[2504.01946v1](http://arxiv.org/abs/2504.01946v1)|null|

|**2025-04-02**|**OpenCodeReasoning: Advancing Data Distillation for Competitive Coding**|Wasi Uddin Ahmad et.al.|[2504.01943v1](http://arxiv.org/abs/2504.01943v1)|null|

|**2025-04-02**|**End-to-End Driving with Online Trajectory Evaluation via BEV World Model**|Yingyan Li et.al.|[2504.01941v1](http://arxiv.org/abs/2504.01941v1)|null|

|**2025-04-02**|**Strengthening Multi-Robot Systems for SAR: Co-Designing Robotics and Communication Towards 6G**|Juan Bravo-Arrabal et.al.|[2504.01940v1](http://arxiv.org/abs/2504.01940v1)|null|

|**2025-04-02**|**Laboratory evaluation of a wearable instrumented headband for rotational head kinematics measurement**|Anu Tripathi et.al.|[2504.01939v1](http://arxiv.org/abs/2504.01939v1)|null|

|**2025-04-02**|**A Unified Approach to Analysis and Design of Denoising Markov Models**|Yinuo Ren et.al.|[2504.01938v1](http://arxiv.org/abs/2504.01938v1)|null|

|**2025-04-02**|**Critical Thinking: Which Kinds of Complexity Govern Optimal Reasoning Length?**|Celine Lee et.al.|[2504.01935v1](http://arxiv.org/abs/2504.01935v1)|null|

|**2025-04-02**|**ILLUME+: Illuminating Unified MLLM with Dual Visual Tokenization and Diffusion Refinement**|Runhui Huang et.al.|[2504.01934v2](http://arxiv.org/abs/2504.01934v2)|null|

|**2025-04-02**|**Hessian-aware Training for Enhancing DNNs Resilience to Parameter Corruptions**|Tahmid Hasan Prato et.al.|[2504.01933v1](http://arxiv.org/abs/2504.01933v1)|null|

|**2025-04-02**|**Review, Refine, Repeat: Understanding Iterative Decoding of AI Agents with Dynamic Evaluation and Selection**|Souradip Chakraborty et.al.|[2504.01931v1](http://arxiv.org/abs/2504.01931v1)|null|

|**2025-04-02**|**A thorough benchmark of automatic text classification: From traditional approaches to large language models**|Washington Cunha et.al.|[2504.01930v1](http://arxiv.org/abs/2504.01930v1)|null|

|**2025-04-02**|**Is the Reversal Curse a Binding Problem? Uncovering Limitations of Transformers from a Basic Generalization Failure**|Boshi Wang et.al.|[2504.01928v1](http://arxiv.org/abs/2504.01928v1)|null|

|**2025-04-02**|**Pairing Anderson motives via formal residues in the Frobenius endomorphism**|Quentin Gazda et.al.|[2504.01926v1](http://arxiv.org/abs/2504.01926v1)|null|

|**2025-04-02**|**Equivariant Spherical CNNs for Accurate Fiber Orientation Distribution Estimation in Neonatal Diffusion MRI with Reduced Acquisition Time**|Haykel Snoussi et.al.|[2504.01925v1](http://arxiv.org/abs/2504.01925v1)|null|

|**2025-04-02**|**Gen-C: Populating Virtual Worlds with Generative Crowds**|Andreas Panayiotou et.al.|[2504.01924v1](http://arxiv.org/abs/2504.01924v1)|null|

|**2025-04-02**|**Sliding Dynamics of Skyrmion Molecular Crystals**|J. C. Bellizotti Souza et.al.|[2504.01923v1](http://arxiv.org/abs/2504.01923v1)|null|

|**2025-04-02**|**Is Less Really More? Fake News Detection with Limited Information**|Zhaoyang Cao et.al.|[2504.01922v1](http://arxiv.org/abs/2504.01922v1)|[link](https://github.com/kappakant/SLIM)|

|**2025-04-02**|**Client Selection in Federated Learning with Data Heterogeneity and Network Latencies**|Harsh Vardhan et.al.|[2504.01921v1](http://arxiv.org/abs/2504.01921v1)|null|

## Edge Computing

### Trust

|Publish Date|Title|Authors|PDF|Code|

| :---: | :---: | :---: | :---: | :---: |

|**2025-04-02**|**Learning from Streaming Video with Orthogonal Gradients**|Tengda Han et.al.|[2504.01961v1](http://arxiv.org/abs/2504.01961v1)|null|

|**2025-04-02**|**Diffusion-Guided Gaussian Splatting for Large-Scale Unconstrained 3D Reconstruction and Novel View Synthesis**|Niluthpol Chowdhury Mithun et.al.|[2504.01960v1](http://arxiv.org/abs/2504.01960v1)|null|

|**2025-04-02**|**Toward Real-world BEV Perception: Depth Uncertainty Estimation via Gaussian Splatting**|Shu-Wei Lu et.al.|[2504.01957v2](http://arxiv.org/abs/2504.01957v2)|null|

|**2025-04-02**|**VideoScene: Distilling Video Diffusion Model to Generate 3D Scenes in One Step**|Hanyang Wang et.al.|[2504.01956v2](http://arxiv.org/abs/2504.01956v2)|null|

|**2025-04-02**|**Scene-Centric Unsupervised Panoptic Segmentation**|Oliver Hahn et.al.|[2504.01955v1](http://arxiv.org/abs/2504.01955v1)|null|

|**2025-04-02**|**Towards Unified Referring Expression Segmentation Across Omni-Level Visual Target Granularities**|Jing Liu et.al.|[2504.01954v1](http://arxiv.org/abs/2504.01954v1)|null|

|**2025-04-02**|**Deep Representation Learning for Unsupervised Clustering of Myocardial Fiber Trajectories in Cardiac Diffusion Tensor Imaging**|Mohini Anand et.al.|[2504.01953v1](http://arxiv.org/abs/2504.01953v1)|null|

|**2025-04-02**|**Image Difference Grounding with Natural Language**|Wenxuan Wang et.al.|[2504.01952v1](http://arxiv.org/abs/2504.01952v1)|null|

|**2025-04-02**|**The LLM Wears Prada: Analysing Gender Bias and Stereotypes through Online Shopping Data**|Massimiliano Luca et.al.|[2504.01951v1](http://arxiv.org/abs/2504.01951v1)|null|

|**2025-04-02**|**PIMDAL: Mitigating the Memory Bottleneck in Data Analytics using a Real Processing-in-Memory System**|Manos Frouzakis et.al.|[2504.01948v1](http://arxiv.org/abs/2504.01948v1)|null|

|**2025-04-02**|**Efficient Federated Learning Tiny Language Models for Mobile Network Feature Prediction**|Daniel Becking et.al.|[2504.01947v1](http://arxiv.org/abs/2504.01947v1)|null|

|**2025-04-02**|**OpenCodeReasoning: Advancing Data Distillation for Competitive Coding**|Wasi Uddin Ahmad et.al.|[2504.01943v1](http://arxiv.org/abs/2504.01943v1)|null|

|**2025-04-02**|**De Sitter entropy: on-shell versus off-shell**|Dmitrii Diakonov et.al.|[2504.01942v1](http://arxiv.org/abs/2504.01942v1)|null|

|**2025-04-02**|**End-to-End Driving with Online Trajectory Evaluation via BEV World Model**|Yingyan Li et.al.|[2504.01941v1](http://arxiv.org/abs/2504.01941v1)|null|

|**2025-04-02**|**Strengthening Multi-Robot Systems for SAR: Co-Designing Robotics and Communication Towards 6G**|Juan Bravo-Arrabal et.al.|[2504.01940v1](http://arxiv.org/abs/2504.01940v1)|null|

|**2025-04-02**|**Fermionic Averaged Circuit Eigenvalue Sampling**|Adrian Chapman et.al.|[2504.01936v1](http://arxiv.org/abs/2504.01936v1)|null|

|**2025-04-02**|**ILLUME+: Illuminating Unified MLLM with Dual Visual Tokenization and Diffusion Refinement**|Runhui Huang et.al.|[2504.01934v2](http://arxiv.org/abs/2504.01934v2)|null|

|**2025-04-02**|**Hessian-aware Training for Enhancing DNNs Resilience to Parameter Corruptions**|Tahmid Hasan Prato et.al.|[2504.01933v1](http://arxiv.org/abs/2504.01933v1)|null|

|**2025-04-02**|**Review, Refine, Repeat: Understanding Iterative Decoding of AI Agents with Dynamic Evaluation and Selection**|Souradip Chakraborty et.al.|[2504.01931v1](http://arxiv.org/abs/2504.01931v1)|null|

|**2025-04-02**|**A thorough benchmark of automatic text classification: From traditional approaches to large language models**|Washington Cunha et.al.|[2504.01930v1](http://arxiv.org/abs/2504.01930v1)|null|

|**2025-04-02**|**Is the Reversal Curse a Binding Problem? Uncovering Limitations of Transformers from a Basic Generalization Failure**|Boshi Wang et.al.|[2504.01928v1](http://arxiv.org/abs/2504.01928v1)|null|

|**2025-04-02**|**Equivariant Spherical CNNs for Accurate Fiber Orientation Distribution Estimation in Neonatal Diffusion MRI with Reduced Acquisition Time**|Haykel Snoussi et.al.|[2504.01925v1](http://arxiv.org/abs/2504.01925v1)|null|

|**2025-04-02**|**Integrated sub-terahertz cavity electro-optic transduction**|Kevin K. S. Multani et.al.|[2504.01920v1](http://arxiv.org/abs/2504.01920v1)|null|

|**2025-04-02**|**Bridging the Linguistic Divide: A Survey on Leveraging Large Language Models for Machine Translation**|Baban Gain et.al.|[2504.01919v2](http://arxiv.org/abs/2504.01919v2)|null|

|**2025-04-02**|**FineLIP: Extending CLIP's Reach via Fine-Grained Alignment with Longer Text Inputs**|Mothilal Asokan et.al.|[2504.01916v1](http://arxiv.org/abs/2504.01916v1)|null|

|**2025-04-02**|**Overcoming Deceptiveness in Fitness Optimization with Unsupervised Quality-Diversity**|Lisa Coiffard et.al.|[2504.01915v1](http://arxiv.org/abs/2504.01915v1)|null|

|**2025-04-02**|**Representing Flow Fields with Divergence-Free Kernels for Reconstruction**|Xingyu Ni et.al.|[2504.01913v1](http://arxiv.org/abs/2504.01913v1)|null|

|**2025-04-02**|**Advancing AI-Scientist Understanding: Making LLM Think Like a Physicist with Interpretable Reasoning**|Yinggan Xu et.al.|[2504.01911v1](http://arxiv.org/abs/2504.01911v1)|null|

|**2025-04-02**|**Accelerating IoV Intrusion Detection: Benchmarking GPU-Accelerated vs CPU-Based ML Libraries**|Furkan Çolhak et.al.|[2504.01905v2](http://arxiv.org/abs/2504.01905v2)|null|

|**2025-04-02**|**STAR-1: Safer Alignment of Reasoning LLMs with 1K Data**|Zijun Wang et.al.|[2504.01903v1](http://arxiv.org/abs/2504.01903v1)|null|

### Scalability

|Publish Date|Title|Authors|PDF|Code|

| :---: | :---: | :---: | :---: | :---: |

|**2025-04-02**|**Learning from Streaming Video with Orthogonal Gradients**|Tengda Han et.al.|[2504.01961v1](http://arxiv.org/abs/2504.01961v1)|null|

|**2025-04-02**|**Diffusion-Guided Gaussian Splatting for Large-Scale Unconstrained 3D Reconstruction and Novel View Synthesis**|Niluthpol Chowdhury Mithun et.al.|[2504.01960v1](http://arxiv.org/abs/2504.01960v1)|null|

|**2025-04-02**|**Toward Real-world BEV Perception: Depth Uncertainty Estimation via Gaussian Splatting**|Shu-Wei Lu et.al.|[2504.01957v2](http://arxiv.org/abs/2504.01957v2)|null|

|**2025-04-02**|**VideoScene: Distilling Video Diffusion Model to Generate 3D Scenes in One Step**|Hanyang Wang et.al.|[2504.01956v2](http://arxiv.org/abs/2504.01956v2)|null|

|**2025-04-02**|**Scene-Centric Unsupervised Panoptic Segmentation**|Oliver Hahn et.al.|[2504.01955v1](http://arxiv.org/abs/2504.01955v1)|null|

|**2025-04-02**|**Towards Unified Referring Expression Segmentation Across Omni-Level Visual Target Granularities**|Jing Liu et.al.|[2504.01954v1](http://arxiv.org/abs/2504.01954v1)|null|

|**2025-04-02**|**Deep Representation Learning for Unsupervised Clustering of Myocardial Fiber Trajectories in Cardiac Diffusion Tensor Imaging**|Mohini Anand et.al.|[2504.01953v1](http://arxiv.org/abs/2504.01953v1)|null|

|**2025-04-02**|**Image Difference Grounding with Natural Language**|Wenxuan Wang et.al.|[2504.01952v1](http://arxiv.org/abs/2504.01952v1)|null|

|**2025-04-02**|**The LLM Wears Prada: Analysing Gender Bias and Stereotypes through Online Shopping Data**|Massimiliano Luca et.al.|[2504.01951v1](http://arxiv.org/abs/2504.01951v1)|null|

|**2025-04-02**|**PIMDAL: Mitigating the Memory Bottleneck in Data Analytics using a Real Processing-in-Memory System**|Manos Frouzakis et.al.|[2504.01948v1](http://arxiv.org/abs/2504.01948v1)|null|

|**2025-04-02**|**Efficient Federated Learning Tiny Language Models for Mobile Network Feature Prediction**|Daniel Becking et.al.|[2504.01947v1](http://arxiv.org/abs/2504.01947v1)|null|

|**2025-04-02**|**OpenCodeReasoning: Advancing Data Distillation for Competitive Coding**|Wasi Uddin Ahmad et.al.|[2504.01943v1](http://arxiv.org/abs/2504.01943v1)|null|

|**2025-04-02**|**De Sitter entropy: on-shell versus off-shell**|Dmitrii Diakonov et.al.|[2504.01942v1](http://arxiv.org/abs/2504.01942v1)|null|

|**2025-04-02**|**End-to-End Driving with Online Trajectory Evaluation via BEV World Model**|Yingyan Li et.al.|[2504.01941v1](http://arxiv.org/abs/2504.01941v1)|null|

|**2025-04-02**|**Strengthening Multi-Robot Systems for SAR: Co-Designing Robotics and Communication Towards 6G**|Juan Bravo-Arrabal et.al.|[2504.01940v1](http://arxiv.org/abs/2504.01940v1)|null|

|**2025-04-02**|**Fermionic Averaged Circuit Eigenvalue Sampling**|Adrian Chapman et.al.|[2504.01936v1](http://arxiv.org/abs/2504.01936v1)|null|

|**2025-04-02**|**ILLUME+: Illuminating Unified MLLM with Dual Visual Tokenization and Diffusion Refinement**|Runhui Huang et.al.|[2504.01934v2](http://arxiv.org/abs/2504.01934v2)|null|

|**2025-04-02**|**Hessian-aware Training for Enhancing DNNs Resilience to Parameter Corruptions**|Tahmid Hasan Prato et.al.|[2504.01933v1](http://arxiv.org/abs/2504.01933v1)|null|

|**2025-04-02**|**Review, Refine, Repeat: Understanding Iterative Decoding of AI Agents with Dynamic Evaluation and Selection**|Souradip Chakraborty et.al.|[2504.01931v1](http://arxiv.org/abs/2504.01931v1)|null|

|**2025-04-02**|**A thorough benchmark of automatic text classification: From traditional approaches to large language models**|Washington Cunha et.al.|[2504.01930v1](http://arxiv.org/abs/2504.01930v1)|null|

|**2025-04-02**|**Is the Reversal Curse a Binding Problem? Uncovering Limitations of Transformers from a Basic Generalization Failure**|Boshi Wang et.al.|[2504.01928v1](http://arxiv.org/abs/2504.01928v1)|null|

|**2025-04-02**|**Equivariant Spherical CNNs for Accurate Fiber Orientation Distribution Estimation in Neonatal Diffusion MRI with Reduced Acquisition Time**|Haykel Snoussi et.al.|[2504.01925v1](http://arxiv.org/abs/2504.01925v1)|null|

|**2025-04-02**|**Integrated sub-terahertz cavity electro-optic transduction**|Kevin K. S. Multani et.al.|[2504.01920v1](http://arxiv.org/abs/2504.01920v1)|null|

|**2025-04-02**|**Bridging the Linguistic Divide: A Survey on Leveraging Large Language Models for Machine Translation**|Baban Gain et.al.|[2504.01919v2](http://arxiv.org/abs/2504.01919v2)|null|

|**2025-04-02**|**FineLIP: Extending CLIP's Reach via Fine-Grained Alignment with Longer Text Inputs**|Mothilal Asokan et.al.|[2504.01916v1](http://arxiv.org/abs/2504.01916v1)|null|

|**2025-04-02**|**Overcoming Deceptiveness in Fitness Optimization with Unsupervised Quality-Diversity**|Lisa Coiffard et.al.|[2504.01915v1](http://arxiv.org/abs/2504.01915v1)|null|

|**2025-04-02**|**Quantum-amplified global-phase spectroscopy on an optical clock transition**|Leon Zaporski et.al.|[2504.01914v1](http://arxiv.org/abs/2504.01914v1)|null|

|**2025-04-02**|**Representing Flow Fields with Divergence-Free Kernels for Reconstruction**|Xingyu Ni et.al.|[2504.01913v1](http://arxiv.org/abs/2504.01913v1)|null|

|**2025-04-02**|**Advancing AI-Scientist Understanding: Making LLM Think Like a Physicist with Interpretable Reasoning**|Yinggan Xu et.al.|[2504.01911v1](http://arxiv.org/abs/2504.01911v1)|null|

|**2025-04-02**|**Accelerating IoV Intrusion Detection: Benchmarking GPU-Accelerated vs CPU-Based ML Libraries**|Furkan Çolhak et.al.|[2504.01905v2](http://arxiv.org/abs/2504.01905v2)|null|

### Performance

|Publish Date|Title|Authors|PDF|Code|

| :---: | :---: | :---: | :---: | :---: |

|**2025-04-02**|**Learning from Streaming Video with Orthogonal Gradients**|Tengda Han et.al.|[2504.01961v1](http://arxiv.org/abs/2504.01961v1)|null|

|**2025-04-02**|**Diffusion-Guided Gaussian Splatting for Large-Scale Unconstrained 3D Reconstruction and Novel View Synthesis**|Niluthpol Chowdhury Mithun et.al.|[2504.01960v1](http://arxiv.org/abs/2504.01960v1)|null|

|**2025-04-02**|**Individual halo bias in models of $f(R)$ gravity**|Jorge Enrique García-Farieta et.al.|[2504.01958v1](http://arxiv.org/abs/2504.01958v1)|null|

|**2025-04-02**|**Toward Real-world BEV Perception: Depth Uncertainty Estimation via Gaussian Splatting**|Shu-Wei Lu et.al.|[2504.01957v2](http://arxiv.org/abs/2504.01957v2)|null|

|**2025-04-02**|**VideoScene: Distilling Video Diffusion Model to Generate 3D Scenes in One Step**|Hanyang Wang et.al.|[2504.01956v2](http://arxiv.org/abs/2504.01956v2)|null|

|**2025-04-02**|**Scene-Centric Unsupervised Panoptic Segmentation**|Oliver Hahn et.al.|[2504.01955v1](http://arxiv.org/abs/2504.01955v1)|null|

|**2025-04-02**|**Towards Unified Referring Expression Segmentation Across Omni-Level Visual Target Granularities**|Jing Liu et.al.|[2504.01954v1](http://arxiv.org/abs/2504.01954v1)|null|

|**2025-04-02**|**Deep Representation Learning for Unsupervised Clustering of Myocardial Fiber Trajectories in Cardiac Diffusion Tensor Imaging**|Mohini Anand et.al.|[2504.01953v1](http://arxiv.org/abs/2504.01953v1)|null|

|**2025-04-02**|**Image Difference Grounding with Natural Language**|Wenxuan Wang et.al.|[2504.01952v1](http://arxiv.org/abs/2504.01952v1)|null|

|**2025-04-02**|**The LLM Wears Prada: Analysing Gender Bias and Stereotypes through Online Shopping Data**|Massimiliano Luca et.al.|[2504.01951v1](http://arxiv.org/abs/2504.01951v1)|null|

|**2025-04-02**|**Comparison of Bayesian methods for extrapolation of treatment effects: a large scale simulation study**|Tristan Fauvel et.al.|[2504.01949v1](http://arxiv.org/abs/2504.01949v1)|null|

|**2025-04-02**|**PIMDAL: Mitigating the Memory Bottleneck in Data Analytics using a Real Processing-in-Memory System**|Manos Frouzakis et.al.|[2504.01948v1](http://arxiv.org/abs/2504.01948v1)|null|

|**2025-04-02**|**Efficient Federated Learning Tiny Language Models for Mobile Network Feature Prediction**|Daniel Becking et.al.|[2504.01947v1](http://arxiv.org/abs/2504.01947v1)|null|

|**2025-04-02**|**OpenCodeReasoning: Advancing Data Distillation for Competitive Coding**|Wasi Uddin Ahmad et.al.|[2504.01943v1](http://arxiv.org/abs/2504.01943v1)|null|

|**2025-04-02**|**De Sitter entropy: on-shell versus off-shell**|Dmitrii Diakonov et.al.|[2504.01942v1](http://arxiv.org/abs/2504.01942v1)|null|

|**2025-04-02**|**End-to-End Driving with Online Trajectory Evaluation via BEV World Model**|Yingyan Li et.al.|[2504.01941v1](http://arxiv.org/abs/2504.01941v1)|null|

|**2025-04-02**|**Strengthening Multi-Robot Systems for SAR: Co-Designing Robotics and Communication Towards 6G**|Juan Bravo-Arrabal et.al.|[2504.01940v1](http://arxiv.org/abs/2504.01940v1)|null|

|**2025-04-02**|**Laboratory evaluation of a wearable instrumented headband for rotational head kinematics measurement**|Anu Tripathi et.al.|[2504.01939v1](http://arxiv.org/abs/2504.01939v1)|null|

|**2025-04-02**|**Fermionic Averaged Circuit Eigenvalue Sampling**|Adrian Chapman et.al.|[2504.01936v1](http://arxiv.org/abs/2504.01936v1)|null|

|**2025-04-02**|**ILLUME+: Illuminating Unified MLLM with Dual Visual Tokenization and Diffusion Refinement**|Runhui Huang et.al.|[2504.01934v2](http://arxiv.org/abs/2504.01934v2)|null|

|**2025-04-02**|**Hessian-aware Training for Enhancing DNNs Resilience to Parameter Corruptions**|Tahmid Hasan Prato et.al.|[2504.01933v1](http://arxiv.org/abs/2504.01933v1)|null|

|**2025-04-02**|**Review, Refine, Repeat: Understanding Iterative Decoding of AI Agents with Dynamic Evaluation and Selection**|Souradip Chakraborty et.al.|[2504.01931v1](http://arxiv.org/abs/2504.01931v1)|null|

|**2025-04-02**|**A thorough benchmark of automatic text classification: From traditional approaches to large language models**|Washington Cunha et.al.|[2504.01930v1](http://arxiv.org/abs/2504.01930v1)|null|

|**2025-04-02**|**Is the Reversal Curse a Binding Problem? Uncovering Limitations of Transformers from a Basic Generalization Failure**|Boshi Wang et.al.|[2504.01928v1](http://arxiv.org/abs/2504.01928v1)|null|

|**2025-04-02**|**Equivariant Spherical CNNs for Accurate Fiber Orientation Distribution Estimation in Neonatal Diffusion MRI with Reduced Acquisition Time**|Haykel Snoussi et.al.|[2504.01925v1](http://arxiv.org/abs/2504.01925v1)|null|

|**2025-04-02**|**Is Less Really More? Fake News Detection with Limited Information**|Zhaoyang Cao et.al.|[2504.01922v1](http://arxiv.org/abs/2504.01922v1)|[link](https://github.com/kappakant/SLIM)|

|**2025-04-02**|**Integrated sub-terahertz cavity electro-optic transduction**|Kevin K. S. Multani et.al.|[2504.01920v1](http://arxiv.org/abs/2504.01920v1)|null|

|**2025-04-02**|**Bridging the Linguistic Divide: A Survey on Leveraging Large Language Models for Machine Translation**|Baban Gain et.al.|[2504.01919v2](http://arxiv.org/abs/2504.01919v2)|null|

|**2025-04-02**|**FineLIP: Extending CLIP's Reach via Fine-Grained Alignment with Longer Text Inputs**|Mothilal Asokan et.al.|[2504.01916v1](http://arxiv.org/abs/2504.01916v1)|null|

|**2025-04-02**|**Overcoming Deceptiveness in Fitness Optimization with Unsupervised Quality-Diversity**|Lisa Coiffard et.al.|[2504.01915v1](http://arxiv.org/abs/2504.01915v1)|null|

### Secure

|Publish Date|Title|Authors|PDF|Code|

| :---: | :---: | :---: | :---: | :---: |

|**2025-04-02**|**Learning from Streaming Video with Orthogonal Gradients**|Tengda Han et.al.|[2504.01961v1](http://arxiv.org/abs/2504.01961v1)|null|

|**2025-04-02**|**Diffusion-Guided Gaussian Splatting for Large-Scale Unconstrained 3D Reconstruction and Novel View Synthesis**|Niluthpol Chowdhury Mithun et.al.|[2504.01960v1](http://arxiv.org/abs/2504.01960v1)|null|

|**2025-04-02**|**Toward Real-world BEV Perception: Depth Uncertainty Estimation via Gaussian Splatting**|Shu-Wei Lu et.al.|[2504.01957v2](http://arxiv.org/abs/2504.01957v2)|null|

|**2025-04-02**|**VideoScene: Distilling Video Diffusion Model to Generate 3D Scenes in One Step**|Hanyang Wang et.al.|[2504.01956v2](http://arxiv.org/abs/2504.01956v2)|null|

|**2025-04-02**|**Scene-Centric Unsupervised Panoptic Segmentation**|Oliver Hahn et.al.|[2504.01955v1](http://arxiv.org/abs/2504.01955v1)|null|

|**2025-04-02**|**Towards Unified Referring Expression Segmentation Across Omni-Level Visual Target Granularities**|Jing Liu et.al.|[2504.01954v1](http://arxiv.org/abs/2504.01954v1)|null|

|**2025-04-02**|**Deep Representation Learning for Unsupervised Clustering of Myocardial Fiber Trajectories in Cardiac Diffusion Tensor Imaging**|Mohini Anand et.al.|[2504.01953v1](http://arxiv.org/abs/2504.01953v1)|null|

|**2025-04-02**|**Image Difference Grounding with Natural Language**|Wenxuan Wang et.al.|[2504.01952v1](http://arxiv.org/abs/2504.01952v1)|null|

|**2025-04-02**|**The LLM Wears Prada: Analysing Gender Bias and Stereotypes through Online Shopping Data**|Massimiliano Luca et.al.|[2504.01951v1](http://arxiv.org/abs/2504.01951v1)|null|

|**2025-04-02**|**PIMDAL: Mitigating the Memory Bottleneck in Data Analytics using a Real Processing-in-Memory System**|Manos Frouzakis et.al.|[2504.01948v1](http://arxiv.org/abs/2504.01948v1)|null|

|**2025-04-02**|**Efficient Federated Learning Tiny Language Models for Mobile Network Feature Prediction**|Daniel Becking et.al.|[2504.01947v1](http://arxiv.org/abs/2504.01947v1)|null|

|**2025-04-02**|**OpenCodeReasoning: Advancing Data Distillation for Competitive Coding**|Wasi Uddin Ahmad et.al.|[2504.01943v1](http://arxiv.org/abs/2504.01943v1)|null|

|**2025-04-02**|**De Sitter entropy: on-shell versus off-shell**|Dmitrii Diakonov et.al.|[2504.01942v1](http://arxiv.org/abs/2504.01942v1)|null|

|**2025-04-02**|**End-to-End Driving with Online Trajectory Evaluation via BEV World Model**|Yingyan Li et.al.|[2504.01941v1](http://arxiv.org/abs/2504.01941v1)|null|

|**2025-04-02**|**Strengthening Multi-Robot Systems for SAR: Co-Designing Robotics and Communication Towards 6G**|Juan Bravo-Arrabal et.al.|[2504.01940v1](http://arxiv.org/abs/2504.01940v1)|null|

|**2025-04-02**|**Fermionic Averaged Circuit Eigenvalue Sampling**|Adrian Chapman et.al.|[2504.01936v1](http://arxiv.org/abs/2504.01936v1)|null|

|**2025-04-02**|**ILLUME+: Illuminating Unified MLLM with Dual Visual Tokenization and Diffusion Refinement**|Runhui Huang et.al.|[2504.01934v2](http://arxiv.org/abs/2504.01934v2)|null|

|**2025-04-02**|**Hessian-aware Training for Enhancing DNNs Resilience to Parameter Corruptions**|Tahmid Hasan Prato et.al.|[2504.01933v1](http://arxiv.org/abs/2504.01933v1)|null|

|**2025-04-02**|**Review, Refine, Repeat: Understanding Iterative Decoding of AI Agents with Dynamic Evaluation and Selection**|Souradip Chakraborty et.al.|[2504.01931v1](http://arxiv.org/abs/2504.01931v1)|null|

|**2025-04-02**|**A thorough benchmark of automatic text classification: From traditional approaches to large language models**|Washington Cunha et.al.|[2504.01930v1](http://arxiv.org/abs/2504.01930v1)|null|

|**2025-04-02**|**Is the Reversal Curse a Binding Problem? Uncovering Limitations of Transformers from a Basic Generalization Failure**|Boshi Wang et.al.|[2504.01928v1](http://arxiv.org/abs/2504.01928v1)|null|

|**2025-04-02**|**Equivariant Spherical CNNs for Accurate Fiber Orientation Distribution Estimation in Neonatal Diffusion MRI with Reduced Acquisition Time**|Haykel Snoussi et.al.|[2504.01925v1](http://arxiv.org/abs/2504.01925v1)|null|

|**2025-04-02**|**Integrated sub-terahertz cavity electro-optic transduction**|Kevin K. S. Multani et.al.|[2504.01920v1](http://arxiv.org/abs/2504.01920v1)|null|

|**2025-04-02**|**Bridging the Linguistic Divide: A Survey on Leveraging Large Language Models for Machine Translation**|Baban Gain et.al.|[2504.01919v2](http://arxiv.org/abs/2504.01919v2)|null|

|**2025-04-02**|**FineLIP: Extending CLIP's Reach via Fine-Grained Alignment with Longer Text Inputs**|Mothilal Asokan et.al.|[2504.01916v1](http://arxiv.org/abs/2504.01916v1)|null|

|**2025-04-02**|**Overcoming Deceptiveness in Fitness Optimization with Unsupervised Quality-Diversity**|Lisa Coiffard et.al.|[2504.01915v1](http://arxiv.org/abs/2504.01915v1)|null|

|**2025-04-02**|**Representing Flow Fields with Divergence-Free Kernels for Reconstruction**|Xingyu Ni et.al.|[2504.01913v1](http://arxiv.org/abs/2504.01913v1)|null|

|**2025-04-02**|**Advancing AI-Scientist Understanding: Making LLM Think Like a Physicist with Interpretable Reasoning**|Yinggan Xu et.al.|[2504.01911v1](http://arxiv.org/abs/2504.01911v1)|null|

|**2025-04-02**|**Accelerating IoV Intrusion Detection: Benchmarking GPU-Accelerated vs CPU-Based ML Libraries**|Furkan Çolhak et.al.|[2504.01905v2](http://arxiv.org/abs/2504.01905v2)|null|

|**2025-04-02**|**STAR-1: Safer Alignment of Reasoning LLMs with 1K Data**|Zijun Wang et.al.|[2504.01903v1](http://arxiv.org/abs/2504.01903v1)|null|

### Efficient

|Publish Date|Title|Authors|PDF|Code|

| :---: | :---: | :---: | :---: | :---: |

|**2025-04-02**|**Learning from Streaming Video with Orthogonal Gradients**|Tengda Han et.al.|[2504.01961v1](http://arxiv.org/abs/2504.01961v1)|null|

|**2025-04-02**|**Diffusion-Guided Gaussian Splatting for Large-Scale Unconstrained 3D Reconstruction and Novel View Synthesis**|Niluthpol Chowdhury Mithun et.al.|[2504.01960v1](http://arxiv.org/abs/2504.01960v1)|null|

|**2025-04-02**|**Toward Real-world BEV Perception: Depth Uncertainty Estimation via Gaussian Splatting**|Shu-Wei Lu et.al.|[2504.01957v2](http://arxiv.org/abs/2504.01957v2)|null|

|**2025-04-02**|**VideoScene: Distilling Video Diffusion Model to Generate 3D Scenes in One Step**|Hanyang Wang et.al.|[2504.01956v2](http://arxiv.org/abs/2504.01956v2)|null|

|**2025-04-02**|**Scene-Centric Unsupervised Panoptic Segmentation**|Oliver Hahn et.al.|[2504.01955v1](http://arxiv.org/abs/2504.01955v1)|null|

|**2025-04-02**|**Towards Unified Referring Expression Segmentation Across Omni-Level Visual Target Granularities**|Jing Liu et.al.|[2504.01954v1](http://arxiv.org/abs/2504.01954v1)|null|

|**2025-04-02**|**Deep Representation Learning for Unsupervised Clustering of Myocardial Fiber Trajectories in Cardiac Diffusion Tensor Imaging**|Mohini Anand et.al.|[2504.01953v1](http://arxiv.org/abs/2504.01953v1)|null|

|**2025-04-02**|**Image Difference Grounding with Natural Language**|Wenxuan Wang et.al.|[2504.01952v1](http://arxiv.org/abs/2504.01952v1)|null|

|**2025-04-02**|**The LLM Wears Prada: Analysing Gender Bias and Stereotypes through Online Shopping Data**|Massimiliano Luca et.al.|[2504.01951v1](http://arxiv.org/abs/2504.01951v1)|null|

|**2025-04-02**|**PIMDAL: Mitigating the Memory Bottleneck in Data Analytics using a Real Processing-in-Memory System**|Manos Frouzakis et.al.|[2504.01948v1](http://arxiv.org/abs/2504.01948v1)|null|

|**2025-04-02**|**Efficient Federated Learning Tiny Language Models for Mobile Network Feature Prediction**|Daniel Becking et.al.|[2504.01947v1](http://arxiv.org/abs/2504.01947v1)|null|

|**2025-04-02**|**OpenCodeReasoning: Advancing Data Distillation for Competitive Coding**|Wasi Uddin Ahmad et.al.|[2504.01943v1](http://arxiv.org/abs/2504.01943v1)|null|

|**2025-04-02**|**De Sitter entropy: on-shell versus off-shell**|Dmitrii Diakonov et.al.|[2504.01942v1](http://arxiv.org/abs/2504.01942v1)|null|

|**2025-04-02**|**End-to-End Driving with Online Trajectory Evaluation via BEV World Model**|Yingyan Li et.al.|[2504.01941v1](http://arxiv.org/abs/2504.01941v1)|null|

|**2025-04-02**|**Strengthening Multi-Robot Systems for SAR: Co-Designing Robotics and Communication Towards 6G**|Juan Bravo-Arrabal et.al.|[2504.01940v1](http://arxiv.org/abs/2504.01940v1)|null|

|**2025-04-02**|**A Unified Approach to Analysis and Design of Denoising Markov Models**|Yinuo Ren et.al.|[2504.01938v1](http://arxiv.org/abs/2504.01938v1)|null|

|**2025-04-02**|**Fermionic Averaged Circuit Eigenvalue Sampling**|Adrian Chapman et.al.|[2504.01936v1](http://arxiv.org/abs/2504.01936v1)|null|

|**2025-04-02**|**ILLUME+: Illuminating Unified MLLM with Dual Visual Tokenization and Diffusion Refinement**|Runhui Huang et.al.|[2504.01934v2](http://arxiv.org/abs/2504.01934v2)|null|

|**2025-04-02**|**Hessian-aware Training for Enhancing DNNs Resilience to Parameter Corruptions**|Tahmid Hasan Prato et.al.|[2504.01933v1](http://arxiv.org/abs/2504.01933v1)|null|

|**2025-04-02**|**Review, Refine, Repeat: Understanding Iterative Decoding of AI Agents with Dynamic Evaluation and Selection**|Souradip Chakraborty et.al.|[2504.01931v1](http://arxiv.org/abs/2504.01931v1)|null|

|**2025-04-02**|**A thorough benchmark of automatic text classification: From traditional approaches to large language models**|Washington Cunha et.al.|[2504.01930v1](http://arxiv.org/abs/2504.01930v1)|null|

|**2025-04-02**|**Is the Reversal Curse a Binding Problem? Uncovering Limitations of Transformers from a Basic Generalization Failure**|Boshi Wang et.al.|[2504.01928v1](http://arxiv.org/abs/2504.01928v1)|null|

|**2025-04-02**|**Equivariant Spherical CNNs for Accurate Fiber Orientation Distribution Estimation in Neonatal Diffusion MRI with Reduced Acquisition Time**|Haykel Snoussi et.al.|[2504.01925v1](http://arxiv.org/abs/2504.01925v1)|null|

|**2025-04-02**|**Client Selection in Federated Learning with Data Heterogeneity and Network Latencies**|Harsh Vardhan et.al.|[2504.01921v1](http://arxiv.org/abs/2504.01921v1)|null|

|**2025-04-02**|**Integrated sub-terahertz cavity electro-optic transduction**|Kevin K. S. Multani et.al.|[2504.01920v1](http://arxiv.org/abs/2504.01920v1)|null|

|**2025-04-02**|**Bridging the Linguistic Divide: A Survey on Leveraging Large Language Models for Machine Translation**|Baban Gain et.al.|[2504.01919v2](http://arxiv.org/abs/2504.01919v2)|null|

|**2025-04-02**|**FineLIP: Extending CLIP's Reach via Fine-Grained Alignment with Longer Text Inputs**|Mothilal Asokan et.al.|[2504.01916v1](http://arxiv.org/abs/2504.01916v1)|null|

|**2025-04-02**|**Overcoming Deceptiveness in Fitness Optimization with Unsupervised Quality-Diversity**|Lisa Coiffard et.al.|[2504.01915v1](http://arxiv.org/abs/2504.01915v1)|null|

|**2025-04-02**|**Representing Flow Fields with Divergence-Free Kernels for Reconstruction**|Xingyu Ni et.al.|[2504.01913v1](http://arxiv.org/abs/2504.01913v1)|null|

|**2025-04-02**|**Advancing AI-Scientist Understanding: Making LLM Think Like a Physicist with Interpretable Reasoning**|Yinggan Xu et.al.|[2504.01911v1](http://arxiv.org/abs/2504.01911v1)|null|

### Privacy

|Publish Date|Title|Authors|PDF|Code|

| :---: | :---: | :---: | :---: | :---: |

|**2025-04-02**|**Learning from Streaming Video with Orthogonal Gradients**|Tengda Han et.al.|[2504.01961v1](http://arxiv.org/abs/2504.01961v1)|null|

|**2025-04-02**|**Diffusion-Guided Gaussian Splatting for Large-Scale Unconstrained 3D Reconstruction and Novel View Synthesis**|Niluthpol Chowdhury Mithun et.al.|[2504.01960v1](http://arxiv.org/abs/2504.01960v1)|null|

|**2025-04-02**|**Toward Real-world BEV Perception: Depth Uncertainty Estimation via Gaussian Splatting**|Shu-Wei Lu et.al.|[2504.01957v2](http://arxiv.org/abs/2504.01957v2)|null|

|**2025-04-02**|**VideoScene: Distilling Video Diffusion Model to Generate 3D Scenes in One Step**|Hanyang Wang et.al.|[2504.01956v2](http://arxiv.org/abs/2504.01956v2)|null|

|**2025-04-02**|**Scene-Centric Unsupervised Panoptic Segmentation**|Oliver Hahn et.al.|[2504.01955v1](http://arxiv.org/abs/2504.01955v1)|null|

|**2025-04-02**|**Towards Unified Referring Expression Segmentation Across Omni-Level Visual Target Granularities**|Jing Liu et.al.|[2504.01954v1](http://arxiv.org/abs/2504.01954v1)|null|

|**2025-04-02**|**Deep Representation Learning for Unsupervised Clustering of Myocardial Fiber Trajectories in Cardiac Diffusion Tensor Imaging**|Mohini Anand et.al.|[2504.01953v1](http://arxiv.org/abs/2504.01953v1)|null|

|**2025-04-02**|**Image Difference Grounding with Natural Language**|Wenxuan Wang et.al.|[2504.01952v1](http://arxiv.org/abs/2504.01952v1)|null|

|**2025-04-02**|**The LLM Wears Prada: Analysing Gender Bias and Stereotypes through Online Shopping Data**|Massimiliano Luca et.al.|[2504.01951v1](http://arxiv.org/abs/2504.01951v1)|null|

|**2025-04-02**|**PIMDAL: Mitigating the Memory Bottleneck in Data Analytics using a Real Processing-in-Memory System**|Manos Frouzakis et.al.|[2504.01948v1](http://arxiv.org/abs/2504.01948v1)|null|

|**2025-04-02**|**Efficient Federated Learning Tiny Language Models for Mobile Network Feature Prediction**|Daniel Becking et.al.|[2504.01947v1](http://arxiv.org/abs/2504.01947v1)|null|

|**2025-04-02**|**OpenCodeReasoning: Advancing Data Distillation for Competitive Coding**|Wasi Uddin Ahmad et.al.|[2504.01943v1](http://arxiv.org/abs/2504.01943v1)|null|

|**2025-04-02**|**De Sitter entropy: on-shell versus off-shell**|Dmitrii Diakonov et.al.|[2504.01942v1](http://arxiv.org/abs/2504.01942v1)|null|

|**2025-04-02**|**End-to-End Driving with Online Trajectory Evaluation via BEV World Model**|Yingyan Li et.al.|[2504.01941v1](http://arxiv.org/abs/2504.01941v1)|null|

|**2025-04-02**|**Strengthening Multi-Robot Systems for SAR: Co-Designing Robotics and Communication Towards 6G**|Juan Bravo-Arrabal et.al.|[2504.01940v1](http://arxiv.org/abs/2504.01940v1)|null|

|**2025-04-02**|**Fermionic Averaged Circuit Eigenvalue Sampling**|Adrian Chapman et.al.|[2504.01936v1](http://arxiv.org/abs/2504.01936v1)|null|

|**2025-04-02**|**ILLUME+: Illuminating Unified MLLM with Dual Visual Tokenization and Diffusion Refinement**|Runhui Huang et.al.|[2504.01934v2](http://arxiv.org/abs/2504.01934v2)|null|

|**2025-04-02**|**Hessian-aware Training for Enhancing DNNs Resilience to Parameter Corruptions**|Tahmid Hasan Prato et.al.|[2504.01933v1](http://arxiv.org/abs/2504.01933v1)|null|

|**2025-04-02**|**Review, Refine, Repeat: Understanding Iterative Decoding of AI Agents with Dynamic Evaluation and Selection**|Souradip Chakraborty et.al.|[2504.01931v1](http://arxiv.org/abs/2504.01931v1)|null|

|**2025-04-02**|**A thorough benchmark of automatic text classification: From traditional approaches to large language models**|Washington Cunha et.al.|[2504.01930v1](http://arxiv.org/abs/2504.01930v1)|null|

|**2025-04-02**|**Is the Reversal Curse a Binding Problem? Uncovering Limitations of Transformers from a Basic Generalization Failure**|Boshi Wang et.al.|[2504.01928v1](http://arxiv.org/abs/2504.01928v1)|null|

|**2025-04-02**|**Equivariant Spherical CNNs for Accurate Fiber Orientation Distribution Estimation in Neonatal Diffusion MRI with Reduced Acquisition Time**|Haykel Snoussi et.al.|[2504.01925v1](http://arxiv.org/abs/2504.01925v1)|null|

|**2025-04-02**|**Integrated sub-terahertz cavity electro-optic transduction**|Kevin K. S. Multani et.al.|[2504.01920v1](http://arxiv.org/abs/2504.01920v1)|null|

|**2025-04-02**|**Bridging the Linguistic Divide: A Survey on Leveraging Large Language Models for Machine Translation**|Baban Gain et.al.|[2504.01919v2](http://arxiv.org/abs/2504.01919v2)|null|

|**2025-04-02**|**FineLIP: Extending CLIP's Reach via Fine-Grained Alignment with Longer Text Inputs**|Mothilal Asokan et.al.|[2504.01916v1](http://arxiv.org/abs/2504.01916v1)|null|

|**2025-04-02**|**Overcoming Deceptiveness in Fitness Optimization with Unsupervised Quality-Diversity**|Lisa Coiffard et.al.|[2504.01915v1](http://arxiv.org/abs/2504.01915v1)|null|

|**2025-04-02**|**Representing Flow Fields with Divergence-Free Kernels for Reconstruction**|Xingyu Ni et.al.|[2504.01913v1](http://arxiv.org/abs/2504.01913v1)|null|

|**2025-04-02**|**Advancing AI-Scientist Understanding: Making LLM Think Like a Physicist with Interpretable Reasoning**|Yinggan Xu et.al.|[2504.01911v1](http://arxiv.org/abs/2504.01911v1)|null|

|**2025-04-02**|**Benchmarking Synthetic Tabular Data: A Multi-Dimensional Evaluation Framework**|Andrey Sidorenko et.al.|[2504.01908v1](http://arxiv.org/abs/2504.01908v1)|[link](https://github.com/mostly-ai/mostlyai-qa)|

|**2025-04-02**|**Accelerating IoV Intrusion Detection: Benchmarking GPU-Accelerated vs CPU-Based ML Libraries**|Furkan Çolhak et.al.|[2504.01905v2](http://arxiv.org/abs/2504.01905v2)|null|

### Reliability

|Publish Date|Title|Authors|PDF|Code|

| :---: | :---: | :---: | :---: | :---: |

|**2025-04-02**|**Learning from Streaming Video with Orthogonal Gradients**|Tengda Han et.al.|[2504.01961v1](http://arxiv.org/abs/2504.01961v1)|null|

|**2025-04-02**|**Diffusion-Guided Gaussian Splatting for Large-Scale Unconstrained 3D Reconstruction and Novel View Synthesis**|Niluthpol Chowdhury Mithun et.al.|[2504.01960v1](http://arxiv.org/abs/2504.01960v1)|null|

|**2025-04-02**|**Toward Real-world BEV Perception: Depth Uncertainty Estimation via Gaussian Splatting**|Shu-Wei Lu et.al.|[2504.01957v2](http://arxiv.org/abs/2504.01957v2)|null|

|**2025-04-02**|**VideoScene: Distilling Video Diffusion Model to Generate 3D Scenes in One Step**|Hanyang Wang et.al.|[2504.01956v2](http://arxiv.org/abs/2504.01956v2)|null|

|**2025-04-02**|**Scene-Centric Unsupervised Panoptic Segmentation**|Oliver Hahn et.al.|[2504.01955v1](http://arxiv.org/abs/2504.01955v1)|null|

|**2025-04-02**|**Towards Unified Referring Expression Segmentation Across Omni-Level Visual Target Granularities**|Jing Liu et.al.|[2504.01954v1](http://arxiv.org/abs/2504.01954v1)|null|

|**2025-04-02**|**Deep Representation Learning for Unsupervised Clustering of Myocardial Fiber Trajectories in Cardiac Diffusion Tensor Imaging**|Mohini Anand et.al.|[2504.01953v1](http://arxiv.org/abs/2504.01953v1)|null|

|**2025-04-02**|**Image Difference Grounding with Natural Language**|Wenxuan Wang et.al.|[2504.01952v1](http://arxiv.org/abs/2504.01952v1)|null|

|**2025-04-02**|**The LLM Wears Prada: Analysing Gender Bias and Stereotypes through Online Shopping Data**|Massimiliano Luca et.al.|[2504.01951v1](http://arxiv.org/abs/2504.01951v1)|null|

|**2025-04-02**|**PIMDAL: Mitigating the Memory Bottleneck in Data Analytics using a Real Processing-in-Memory System**|Manos Frouzakis et.al.|[2504.01948v1](http://arxiv.org/abs/2504.01948v1)|null|

|**2025-04-02**|**Efficient Federated Learning Tiny Language Models for Mobile Network Feature Prediction**|Daniel Becking et.al.|[2504.01947v1](http://arxiv.org/abs/2504.01947v1)|null|

|**2025-04-02**|**OpenCodeReasoning: Advancing Data Distillation for Competitive Coding**|Wasi Uddin Ahmad et.al.|[2504.01943v1](http://arxiv.org/abs/2504.01943v1)|null|

|**2025-04-02**|**De Sitter entropy: on-shell versus off-shell**|Dmitrii Diakonov et.al.|[2504.01942v1](http://arxiv.org/abs/2504.01942v1)|null|

|**2025-04-02**|**End-to-End Driving with Online Trajectory Evaluation via BEV World Model**|Yingyan Li et.al.|[2504.01941v1](http://arxiv.org/abs/2504.01941v1)|null|

|**2025-04-02**|**Strengthening Multi-Robot Systems for SAR: Co-Designing Robotics and Communication Towards 6G**|Juan Bravo-Arrabal et.al.|[2504.01940v1](http://arxiv.org/abs/2504.01940v1)|null|

|**2025-04-02**|**Fermionic Averaged Circuit Eigenvalue Sampling**|Adrian Chapman et.al.|[2504.01936v1](http://arxiv.org/abs/2504.01936v1)|null|

|**2025-04-02**|**ILLUME+: Illuminating Unified MLLM with Dual Visual Tokenization and Diffusion Refinement**|Runhui Huang et.al.|[2504.01934v2](http://arxiv.org/abs/2504.01934v2)|null|

|**2025-04-02**|**Hessian-aware Training for Enhancing DNNs Resilience to Parameter Corruptions**|Tahmid Hasan Prato et.al.|[2504.01933v1](http://arxiv.org/abs/2504.01933v1)|null|

|**2025-04-02**|**Review, Refine, Repeat: Understanding Iterative Decoding of AI Agents with Dynamic Evaluation and Selection**|Souradip Chakraborty et.al.|[2504.01931v1](http://arxiv.org/abs/2504.01931v1)|null|

|**2025-04-02**|**A thorough benchmark of automatic text classification: From traditional approaches to large language models**|Washington Cunha et.al.|[2504.01930v1](http://arxiv.org/abs/2504.01930v1)|null|

|**2025-04-02**|**Is the Reversal Curse a Binding Problem? Uncovering Limitations of Transformers from a Basic Generalization Failure**|Boshi Wang et.al.|[2504.01928v1](http://arxiv.org/abs/2504.01928v1)|null|

|**2025-04-02**|**Equivariant Spherical CNNs for Accurate Fiber Orientation Distribution Estimation in Neonatal Diffusion MRI with Reduced Acquisition Time**|Haykel Snoussi et.al.|[2504.01925v1](http://arxiv.org/abs/2504.01925v1)|null|

|**2025-04-02**|**Integrated sub-terahertz cavity electro-optic transduction**|Kevin K. S. Multani et.al.|[2504.01920v1](http://arxiv.org/abs/2504.01920v1)|null|

|**2025-04-02**|**Bridging the Linguistic Divide: A Survey on Leveraging Large Language Models for Machine Translation**|Baban Gain et.al.|[2504.01919v2](http://arxiv.org/abs/2504.01919v2)|null|

|**2025-04-02**|**FineLIP: Extending CLIP's Reach via Fine-Grained Alignment with Longer Text Inputs**|Mothilal Asokan et.al.|[2504.01916v1](http://arxiv.org/abs/2504.01916v1)|null|

|**2025-04-02**|**Overcoming Deceptiveness in Fitness Optimization with Unsupervised Quality-Diversity**|Lisa Coiffard et.al.|[2504.01915v1](http://arxiv.org/abs/2504.01915v1)|null|

|**2025-04-02**|**Representing Flow Fields with Divergence-Free Kernels for Reconstruction**|Xingyu Ni et.al.|[2504.01913v1](http://arxiv.org/abs/2504.01913v1)|null|

|**2025-04-02**|**Advancing AI-Scientist Understanding: Making LLM Think Like a Physicist with Interpretable Reasoning**|Yinggan Xu et.al.|[2504.01911v1](http://arxiv.org/abs/2504.01911v1)|null|

|**2025-04-02**|**Accelerating IoV Intrusion Detection: Benchmarking GPU-Accelerated vs CPU-Based ML Libraries**|Furkan Çolhak et.al.|[2504.01905v2](http://arxiv.org/abs/2504.01905v2)|null|

|**2025-04-02**|**STAR-1: Safer Alignment of Reasoning LLMs with 1K Data**|Zijun Wang et.al.|[2504.01903v1](http://arxiv.org/abs/2504.01903v1)|null|

### Edge Computing

|Publish Date|Title|Authors|PDF|Code|

| :---: | :---: | :---: | :---: | :---: |

|**2025-04-02**|**Learning from Streaming Video with Orthogonal Gradients**|Tengda Han et.al.|[2504.01961v1](http://arxiv.org/abs/2504.01961v1)|null|

|**2025-04-02**|**Diffusion-Guided Gaussian Splatting for Large-Scale Unconstrained 3D Reconstruction and Novel View Synthesis**|Niluthpol Chowdhury Mithun et.al.|[2504.01960v1](http://arxiv.org/abs/2504.01960v1)|null|

|**2025-04-02**|**Slot-Level Robotic Placement via Visual Imitation from Single Human Video**|Dandan Shan et.al.|[2504.01959v1](http://arxiv.org/abs/2504.01959v1)|null|

|**2025-04-02**|**Toward Real-world BEV Perception: Depth Uncertainty Estimation via Gaussian Splatting**|Shu-Wei Lu et.al.|[2504.01957v2](http://arxiv.org/abs/2504.01957v2)|null|

|**2025-04-02**|**VideoScene: Distilling Video Diffusion Model to Generate 3D Scenes in One Step**|Hanyang Wang et.al.|[2504.01956v2](http://arxiv.org/abs/2504.01956v2)|null|

|**2025-04-02**|**Scene-Centric Unsupervised Panoptic Segmentation**|Oliver Hahn et.al.|[2504.01955v1](http://arxiv.org/abs/2504.01955v1)|null|

|**2025-04-02**|**Towards Unified Referring Expression Segmentation Across Omni-Level Visual Target Granularities**|Jing Liu et.al.|[2504.01954v1](http://arxiv.org/abs/2504.01954v1)|null|

|**2025-04-02**|**Deep Representation Learning for Unsupervised Clustering of Myocardial Fiber Trajectories in Cardiac Diffusion Tensor Imaging**|Mohini Anand et.al.|[2504.01953v1](http://arxiv.org/abs/2504.01953v1)|null|

|**2025-04-02**|**Image Difference Grounding with Natural Language**|Wenxuan Wang et.al.|[2504.01952v1](http://arxiv.org/abs/2504.01952v1)|null|

|**2025-04-02**|**The LLM Wears Prada: Analysing Gender Bias and Stereotypes through Online Shopping Data**|Massimiliano Luca et.al.|[2504.01951v1](http://arxiv.org/abs/2504.01951v1)|null|

|**2025-04-02**|**Comparison of Bayesian methods for extrapolation of treatment effects: a large scale simulation study**|Tristan Fauvel et.al.|[2504.01949v1](http://arxiv.org/abs/2504.01949v1)|null|

|**2025-04-02**|**PIMDAL: Mitigating the Memory Bottleneck in Data Analytics using a Real Processing-in-Memory System**|Manos Frouzakis et.al.|[2504.01948v1](http://arxiv.org/abs/2504.01948v1)|null|

|**2025-04-02**|**Efficient Federated Learning Tiny Language Models for Mobile Network Feature Prediction**|Daniel Becking et.al.|[2504.01947v1](http://arxiv.org/abs/2504.01947v1)|null|

|**2025-04-02**|**OpenCodeReasoning: Advancing Data Distillation for Competitive Coding**|Wasi Uddin Ahmad et.al.|[2504.01943v1](http://arxiv.org/abs/2504.01943v1)|null|

|**2025-04-02**|**De Sitter entropy: on-shell versus off-shell**|Dmitrii Diakonov et.al.|[2504.01942v1](http://arxiv.org/abs/2504.01942v1)|null|

|**2025-04-02**|**End-to-End Driving with Online Trajectory Evaluation via BEV World Model**|Yingyan Li et.al.|[2504.01941v1](http://arxiv.org/abs/2504.01941v1)|null|

|**2025-04-02**|**Strengthening Multi-Robot Systems for SAR: Co-Designing Robotics and Communication Towards 6G**|Juan Bravo-Arrabal et.al.|[2504.01940v1](http://arxiv.org/abs/2504.01940v1)|null|

|**2025-04-02**|**Laboratory evaluation of a wearable instrumented headband for rotational head kinematics measurement**|Anu Tripathi et.al.|[2504.01939v1](http://arxiv.org/abs/2504.01939v1)|null|

|**2025-04-02**|**A Unified Approach to Analysis and Design of Denoising Markov Models**|Yinuo Ren et.al.|[2504.01938v1](http://arxiv.org/abs/2504.01938v1)|null|

|**2025-04-02**|**Fermionic Averaged Circuit Eigenvalue Sampling**|Adrian Chapman et.al.|[2504.01936v1](http://arxiv.org/abs/2504.01936v1)|null|

|**2025-04-02**|**ILLUME+: Illuminating Unified MLLM with Dual Visual Tokenization and Diffusion Refinement**|Runhui Huang et.al.|[2504.01934v2](http://arxiv.org/abs/2504.01934v2)|null|

|**2025-04-02**|**Hessian-aware Training for Enhancing DNNs Resilience to Parameter Corruptions**|Tahmid Hasan Prato et.al.|[2504.01933v1](http://arxiv.org/abs/2504.01933v1)|null|

|**2025-04-02**|**Review, Refine, Repeat: Understanding Iterative Decoding of AI Agents with Dynamic Evaluation and Selection**|Souradip Chakraborty et.al.|[2504.01931v1](http://arxiv.org/abs/2504.01931v1)|null|

|**2025-04-02**|**A thorough benchmark of automatic text classification: From traditional approaches to large language models**|Washington Cunha et.al.|[2504.01930v1](http://arxiv.org/abs/2504.01930v1)|null|

|**2025-04-02**|**Is the Reversal Curse a Binding Problem? Uncovering Limitations of Transformers from a Basic Generalization Failure**|Boshi Wang et.al.|[2504.01928v1](http://arxiv.org/abs/2504.01928v1)|null|

|**2025-04-02**|**Equivariant Spherical CNNs for Accurate Fiber Orientation Distribution Estimation in Neonatal Diffusion MRI with Reduced Acquisition Time**|Haykel Snoussi et.al.|[2504.01925v1](http://arxiv.org/abs/2504.01925v1)|null|

|**2025-04-02**|**Gen-C: Populating Virtual Worlds with Generative Crowds**|Andreas Panayiotou et.al.|[2504.01924v1](http://arxiv.org/abs/2504.01924v1)|null|

|**2025-04-02**|**Is Less Really More? Fake News Detection with Limited Information**|Zhaoyang Cao et.al.|[2504.01922v1](http://arxiv.org/abs/2504.01922v1)|[link](https://github.com/kappakant/SLIM)|

|**2025-04-02**|**Client Selection in Federated Learning with Data Heterogeneity and Network Latencies**|Harsh Vardhan et.al.|[2504.01921v1](http://arxiv.org/abs/2504.01921v1)|null|

|**2025-04-02**|**Integrated sub-terahertz cavity electro-optic transduction**|Kevin K. S. Multani et.al.|[2504.01920v1](http://arxiv.org/abs/2504.01920v1)|null|