Diffusion

• Aligning Target-Aware Molecule Diffusion Models with Exact Energy Optimization
• Molecule Design by Latent Prompt Transformer
• TurboHopp: Accelerated Molecule Scaffold Hopping with Consistency Models
• Conditional Synthesis of 3D Molecules with Time Correction Sampler
• UniIF: Unified Molecule Inverse Folding
• QVAE-Mole: The Quantum VAE with Spherical Latent Variable Learning for 3-D Molecule Generation
• Score-based 3D molecule generation with neural fields
• Molecule Generation with Fragment Retrieval Augmentation
• FlexSBDD: Structure-Based Drug Design with Flexible Protein Modeling
• ProtGO: Function-Guided Protein Modeling for Unified Representation Learning
• Learning Complete Protein Representation by Dynamically Coupling of Sequence and Structure

Diffusion

• Clustering then Propagation: Select Better Anchors for Knowledge Graph Embedding
• Knowledge Graph Completion by Intermediate Variables Regularization
• KG-FIT: Knowledge Graph Fine-Tuning Upon Open-World Knowledge
• Text2NKG: Fine-Grained N-ary Relation Extraction for N-ary relational Knowledge Graph Construction
• KnowGPT: Knowledge Graph based Prompting for Large Language Models
• Plan-on-Graph: Self-Correcting Adaptive Planning of Large Language Model on Knowledge Graphs
• A Prompt-Based Knowledge Graph Foundation Model for Universal In-Context Reasoning
• GraphVis: Boosting LLMs with Visual Knowledge Graph Integration
• UrbanKGent: A Unified Large Language Model Agent Framework for Urban Knowledge Graph Construction

Diffusion

• Scene Graph Generation with Role-Playing Large Language Models
• Adaptive Visual Scene Understanding: Incremental Scene Graph Generation
• Scene Graph Disentanglement and Composition for Generalizable Complex Image Generation
• SG-Nav: Online 3D Scene Graph Prompting for LLM-based Zero-shot Object Navigation
• Multiview Scene Graph

Diffusion

• Genetic-guided GFlowNets for Sample Efficient Molecular Optimization
• Sample Efficient Bayesian Learning of Causal Graphs from Interventions
• Are Your Models Still Fair? Fairness Attacks on Graph Neural Networks via Node Injections
• Probabilistic Weather Forecasting with Hierarchical Graph Neural Networks
• Unitary Convolutions for Learning on Graphs and Groups
• GRANOLA: Adaptive Normalization for Graph Neural Networks
• Mind the Graph When Balancing Data for Fairness or Robustness
• Graph Structure Inference with BAM: Neural Dependency Processing via Bilinear Attention
• Tracing Hyperparameter Dependencies for Model Parsing via Learnable Graph Pooling Network
• DistrictNet: Decision-aware learning for geographical districting
• Analysis of Corrected Graph Convolutions
• GITA: Graph to Visual and Textual Integration for Vision-Language Graph Reasoning
• Microstructures and Accuracy of Graph Recall by Large Language Models
• Fair GLASSO: Estimating Fair Graphical Models with Unbiased Statistical Behavior
• Continuous Partitioning for Graph-Based Semi-Supervised Learning
• On Neural Networks as Infinite Tree-Structured Probabilistic Graphical Models
• What Is Missing For Graph Homophily? Disentangling Graph Homophily For Graph Neural Networks
• Gradient Rewiring for Editable Graph Neural Network Training
• Graph Learning for Numeric Planning
• Towards Harmless Rawlsian Fairness Regardless of Demographic Prior
• DFA-GNN: Forward Learning of Graph Neural Networks by Direct Feedback Alignment
• Dissecting the Failure of Invariant Learning on Graphs
• Replay-and-Forget-Free Graph Class-Incremental Learning: A Task Profiling and Prompting Approach
• Cost-efficient Knowledge-based Question Answering with Large Language Models
• An Efficient Memory Module for Graph Few-Shot Class-Incremental Learning
• Efficient Policy Evaluation Across Multiple Different Experimental Datasets
• Can Graph Neural Networks Expose Training Data Properties? An Efficient Risk Assessment Approach
• Stochastic Taylor Derivative Estimator: Efficient amortization for arbitrary differential operators
• Efficient Streaming Algorithms for Graphlet Sampling
• Pin-Tuning: Parameter-Efficient In-Context Tuning for Few-Shot Molecular Property Prediction
• Private Edge Density Estimation for Random Graphs: Optimal, Efficient and Robust
• Gaussian Graph Network: Learning Efficient and Generalizable Gaussian Representations from Multi-view Images
• GDeR: Safeguarding Efficiency, Balancing, and Robustness via Prototypical Graph Pruning
• Graph Edit Distance with General Costs Using Neural Set Divergence
• What Matters in Graph Class Incremental Learning? An Information Preservation Perspective
• Generative Modelling of Structurally Constrained Graphs
• Intruding with Words: Towards Understanding Graph Injection Attacks at the Text Level
• Boosting Graph Pooling with Persistent Homology
• GaussianCut: Interactive segmentation via graph cut for 3D Gaussian Splatting
• ARC: A Generalist Graph Anomaly Detector with In-Context Learning
• Leveraging Tumor Heterogeneity: Heterogeneous Graph Representation Learning for Cancer Survival Prediction in Whole Slide Images
• Road Network Representation Learning with the Third Law of Geography
• Bayesian Optimization of Functions over Node Subsets in Graphs
• IF-Font: Ideographic Description Sequence-Following Font Generation
• Almost Surely Asymptotically Constant Graph Neural Networks
• Distributed-Order Fractional Graph Operating Network
• DiGRAF: Diffeomorphic Graph-Adaptive Activation Function
• Generalizing CNNs to graphs with learnable neighborhood quantization
• InstructG2I: Synthesizing Images from Multimodal Attributed Graphs
• On the Scalability of GNNs for Molecular Graphs
• Spiking Graph Neural Network on Riemannian Manifolds
• Rethinking Reconstruction-based Graph-Level Anomaly Detection: Limitations and a Simple Remedy
• DeTikZify: Synthesizing Graphics Programs for Scientific Figures and Sketches with TikZ
• Idiographic Personality Gaussian Process for Psychological Assessment
• What do Graph Neural Networks learn? Insights from Tropical Geometry
• Accelerating Non-Maximum Suppression: A Graph Theory Perspective
• Cryptographic Hardness of Score Estimation
• Graph Neural Networks and Arithmetic Circuits
• Probabilistic Graph Rewiring via Virtual Nodes
• Fast Graph Sharpness-Aware Minimization for Enhancing and Accelerating Few-Shot Node Classification
• SpelsNet: Surface Primitive Elements Segmentation by B-Rep Graph Structure Supervision
• Differentiable Task Graph Learning: Procedural Activity Representation and Online Mistake Detection from Egocentric Videos
• Exploring Consistency in Graph Representations: from Graph Kernels to Graph Neural Networks
• Empowering Active Learning for 3D Molecular Graphs with Geometric Graph Isomorphism
• UniGAD: Unifying Multi-level Graph Anomaly Detection
• GraphCroc: Cross-Correlation Autoencoder for Graph Structural Reconstruction
• Visual Data Diagnosis and Debiasing with Concept Graphs
• Deep Graph Mating
• Energy-based Epistemic Uncertainty for Graph Neural Networks
• Integrating GNN and Neural ODEs for Estimating Non-Reciprocal Two-Body Interactions in Mixed-Species Collective Motion
• Hamba: Single-view 3D Hand Reconstruction with Graph-guided Bi-Scanning Mamba
• Similarity-Navigated Conformal Prediction for Graph Neural Networks
• Navigable Graphs for High-Dimensional Nearest Neighbor Search: Constructions and Limits
• Graph Classification via Reference Distribution Learning: Theory and Practice
• Continuous Product Graph Neural Networks
• Uncovering the Redundancy in Graph Self-supervised Learning Models
• Logical characterizations of recurrent graph neural networks with reals and floats
• Graph Neural Flows for Unveiling Systemic Interactions Among Irregularly Sampled Time Series
• DropEdge not Foolproof: Effective Augmentation Method for Signed Graph Neural Networks
• DeepITE: Designing Variational Graph Autoencoders for Intervention Target Estimation
• A Structure-Aware Framework for Learning Device Placements on Computation Graphs
• Fairness-Aware Estimation of Graphical Models
• Aligning Embeddings and Geometric Random Graphs: Informational Results and Computational Approaches for the Procrustes-Wasserstein Problem
• Spatio-Spectral Graph Neural Networks
• Motion Graph Unleashed: A Novel Approach to Video Prediction
• Bridge the Points: Graph-based Few-shot Segment Anything Semantically
• Deep Graph Neural Networks via Posteriori-Sampling-based Node-Adaptative Residual Module
• RAGraph: A General Retrieval-Augmented Graph Learning Framework
• Learning on Large Graphs using Intersecting Communities
• DARG: Dynamic Evaluation of Large Language Models via Adaptive Reasoning Graph
• UGC: Universal Graph Coarsening
• Theoretical and Empirical Insights into the Origins of Degree Bias in Graph Neural Networks
• LLaMo: Large Language Model-based Molecular Graph Assistant
• Are Graph Neural Networks Optimal Approximation Algorithms?
• Spectral Graph Pruning Against Over-Squashing and Over-Smoothing
• The Map Equation Goes Neural: Mapping Network Flows with Graph Neural Networks
• Graph Coarsening with Message-Passing Guarantees
• CSPG: Crossing Sparse Proximity Graphs for Approximate Nearest Neighbor Search
• Dynamic Rescaling for Training GNNs
• An End-To-End Graph Attention Network Hashing for Cross-Modal Retrieval
• EGODE: An Event-attended Graph ODE Framework for Modeling Rigid Dynamics
• Robust Offline Active Learning on Graphs
• Active design of two-photon holographic stimulation for identifying neural population dynamics
• Automated Label Unification for Multi-Dataset Semantic Segmentation with GNNs
• G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answering
• The Intelligible and Effective Graph Neural Additive Network
• HGDL: Heterogeneous Graph Label Distribution Learning
• A Topology-aware Graph Coarsening Framework for Continual Graph Learning
• Robust Graph Neural Networks via Unbiased Aggregation
• Challenges of Generating Structurally Diverse Graphs
• Mixture of Link Predictors on Graphs
• Regression under demographic parity constraints via unlabeled post-processing
• Graph neural networks and non-commuting operators
• Graph-based Uncertainty Metrics for Long-form Language Model Generations
• Graph-enhanced Optimizers for Structure-aware Recommendation Embedding Evolution
• Learning Plaintext-Ciphertext Cryptographic Problems via ANF-based SAT Instance Representation
• Customized Subgraph Selection and Encoding for Drug-drug Interaction Prediction
• FUGAL: Feature-fortified Unrestricted Graph Alignment
• Graphcode: Learning from multiparameter persistent homology using graph neural networks
• Stochastic contextual bandits with graph feedback: from independence number to MAS number
• Generative Semi-supervised Graph Anomaly Detection
• GraphMorph: Tubular Structure Extraction by Morphing Predicted Graphs
• Non-convolutional graph neural networks.
• Linear Uncertainty Quantification of Graphical Model Inference
• Graph Neural Networks Do Not Always Oversmooth
• Schur Nets: exploiting local structure for equivariance in higher order graph neural networks
• ETO:Efficient Transformer-based Local Feature Matching by Organizing Multiple Homography Hypotheses
• Neural P$^3$M: A Long-Range Interaction Modeling Enhancer for Geometric GNNs

Diffusion

• Amortized Active Causal Induction with Deep Reinforcement Learning
• Causal Discovery from Event Sequences by Local Cause-Effect Attribution
• Hybrid Top-Down Global Causal Discovery with Local Search for Linear and Nonlinear Additive Noise Models
• Conditional Generative Models are Sufficient to Sample from Any Causal Effect Estimand
• Partial Structure Discovery is Sufficient for No-regret Learning in Causal Bandits
• Disentangled Representation Learning in Non-Markovian Causal Systems
• On Causal Discovery in the Presence of Deterministic Relations
• Learning the Latent Causal Structure for Modeling Label Noise
• A Simple yet Scalable Granger Causal Structural Learning Approach for Topological Event Sequences
• Interventional Causal Discovery in a Mixture of DAGs
• Identifying General Mechanism Shifts in Linear Causal Representations
• Causal Effect Identification in a Sub-Population with Latent Variables
• Learning Linear Causal Representations from General Environments: Identifiability and Intrinsic Ambiguity
• Causal discovery with endogenous context variables
• On the Complexity of Identification in Linear Structural Causal Models
• Learning Mixtures of Unknown Causal Interventions
• Sample Complexity of Interventional Causal Representation Learning
• Linear Causal Bandits: Unknown Graph and Soft Interventions
• Identifying Causal Effects Under Functional Dependencies
• A Local Method for Satisfying Interventional Fairness with Partially Known Causal Graphs
• Consistency of Neural Causal Partial Identification
• On the Parameter Identifiability of Partially Observed Linear Causal Models
• QWO: Speeding Up Permutation-Based Causal Discovery in LiGAMs
• Complete Graphical Criterion for Sequential Covariate Adjustment in Causal Inference
• CausalStock: Deep End-to-end Causal Discovery for News-driven Multi-stock Movement Prediction

Diffusion

• **Awesome-LLMs-ICLR-24**
• Awesome **NeurIPS'24** ***Molecular ML*** Paper Collection
• **Awesome ICML 2024 Graph Paper Collection**
• **Awesome ICLR 2024 Graph Paper Collection**

• Weisfeiler and Leman Go Loopy: A New Hierarchy for Graph Representational Learning
• Unifying Homophily and Heterophily for Spectral Graph Neural Networks via Triple Filter Ensembles
• On the Impact of Feature Heterophily on Link Prediction with Graph Neural Networks
• Slack-Free Spiking Neural Network Formulation for Hypergraph Minimum Vertex Cover
• Ada-MSHyper: Adaptive Multi-Scale Hypergraph Transformer for Time Series Forecasting
• Assembly Fuzzy Representation on Hypergraph for Open-Set 3D Object Retrieval
• On the Expressivity and Sample Complexity of Node-Individualized Graph Neural Networks
• On the Expressive Power of Tree-Structured Probabilistic Circuits
• Bridging OOD Detection and Generalization: A Graph-Theoretic View
• Compositional PAC-Bayes: Generalization of GNNs with persistence and beyond
• Improving Generalization of Dynamic Graph Learning via Environment Prompt
• Variational Flow Matching for Graph Generation
• ET-Flow: Equivariant Flow-Matching for Molecular Conformer Generation
• Approximately Equivariant Neural Processes
• Equivariant Machine Learning on Graphs with Nonlinear Spectral Filters
• Generalized Protein Pocket Generation with Prior-Informed Flow Matching
• A probability contrastive learning framework for 3D molecular representation learning
• How Molecules Impact Cells: Unlocking Contrastive PhenoMolecular Retrieval
• Inference via Interpolation: Contrastive Representations Provably Enable Planning and Inference
• Exploitation of a Latent Mechanism in Graph Contrastive Learning: Representation Scattering
• FUG: Feature-Universal Graph Contrastive Pre-training for Graphs with Diverse Node Features
• Unified Graph Augmentations for Generalized Contrastive Learning on Graphs
• Are High-Degree Representations Really Unnecessary in Equivariant Graph Neural Networks?
• Semi-Open 3D Object Retrieval via Hierarchical Equilibrium on Hypergraph
• Leveraging Contrastive Learning for Enhanced Node Representations in Tokenized Graph Transformers
• Boosting Sample Efficiency and Generalization in Multi-agent Reinforcement Learning via Equivariance
• Topological Generalization Bounds for Discrete-Time Stochastic Optimization Algorithms
• A Flexible, Equivariant Framework for Subgraph GNNs via Graph Products and Graph Coarsening
• Equivariant Blurring Diffusion for Hierarchical Molecular Conformer Generation
• Identifiability Guarantees for Causal Disentanglement from Purely Observational Data
• Equivariant spatio-hemispherical networks for diffusion MRI deconvolution
• Equivariant Neural Diffusion for Molecule Generation
• Reconstruct and Match: Out-of-Distribution Robustness via Topological Homogeneity
• Revisiting Score Propagation in Graph Out-of-Distribution Detection
• PURE: Prompt Evolution with Graph ODE for Out-of-distribution Fluid Dynamics Modeling
• Efficient Graph Matching for Correlated Stochastic Block Models
• Iteratively Refined Early Interaction Alignment for Subgraph Matching based Graph Retrieval
• FlowLLM: Flow Matching for Material Generation with Large Language Models as Base Distributions
• Fisher Flow Matching for Generative Modeling over Discrete Data
• Embedding Dimension of Contrastive Learning and $k$-Nearest Neighbors

Diffusion

• Graph Diffusion Transformers for Multi-Conditional Molecular Generation
• NaRCan: Natural Refined Canonical Image with Integration of Diffusion Prior for Video Editing
• Learning-to-Cache: Accelerating Diffusion Transformer via Layer Caching
• Discrete-state Continuous-time Diffusion for Graph Generation
• Pard: Permutation-Invariant Autoregressive Diffusion for Graph Generation
• DiffusionBlend: Learning 3D Image Prior through Position-aware Diffusion Score Blending for 3D Computed Tomography Reconstruction
• Diffusion Twigs with Loop Guidance for Conditional Graph Generation
• Graph Neural Networks Need Cluster-Normalize-Activate Modules
• Reprogramming Pretrained Target-Specific Diffusion Models for Dual-Target Drug Design
• Visual Decoding and Reconstruction via EEG Embeddings with Guided Diffusion
• Geometric Trajectory Diffusion Models
• DiffCut: Catalyzing Zero-Shot Semantic Segmentation with Diffusion Features and Recursive Normalized Cut
• DiffuBox: Refining 3D Object Detection with Point Diffusion
• Graph Diffusion Policy Optimization
• Revisiting Self-Supervised Heterogeneous Graph Learning from Spectral Clustering Perspective
• Cluster-wise Graph Transformer with Dual-granularity Kernelized Attention
• TFGDA: Exploring Topology and Feature Alignment in Semi-supervised Graph Domain Adaptation through Robust Clustering
• How Does Message Passing Improve Collaborative Filtering?
• Sequential Signal Mixing Aggregation for Message Passing Graph Neural Networks
• Pure Message Passing Can Estimate Common Neighbor for Link Prediction
• Towards Dynamic Message Passing on Graphs
• Adapting Diffusion Models for Improved Prompt Compliance and Controllable Image Synthesis
• Unifying Generation and Prediction on Graphs with Latent Graph Diffusion
• SubgDiff: A Subgraph Diffusion Model to Improve Molecular Representation Learning
• Faster Local Solvers for Graph Diffusion Equations
• From Dictionary to Tensor: A Scalable Multi-View Subspace Clustering Framework with Triple Information Enhancement
• HC-GAE: The Hierarchical Cluster-based Graph Auto-Encoder for Graph Representation Learning
• ProTransformer: Robustify Transformers via Plug-and-Play Paradigm
• Enhancing Graph Transformers with Hierarchical Distance Structural Encoding
• Towards Principled Graph Transformers
• Even Sparser Graph Transformers
• Fast Tree-Field Integrators: From Low Displacement Rank to Topological Transformers
• $\\textit{NeuroPath}$: A Neural Pathway Transformer for Joining the Dots of Human Connectomes
• Understanding Transformer Reasoning Capabilities via Graph Algorithms
• Low-Rank Optimal Transport through Factor Relaxation with Latent Coupling
• Fairness in Social Influence Maximization via Optimal Transport
• Unsupervised Homography Estimation on Multimodal Image Pair via Alternating Optimization
• Beyond Redundancy: Information-aware Unsupervised Multiplex Graph Structure Learning
• Graph-based Unsupervised Disentangled Representation Learning via Multimodal Large Language Models
• DisenGCD: A Meta Multigraph-assisted Disentangled Graph Learning Framework for Cognitive Diagnosis
• Long-range Meta-path Search on Large-scale Heterogeneous Graphs
• Cell ontology guided transcriptome foundation model
• Supra-Laplacian Encoding for Transformer on Dynamic Graphs
• Long-range Brain Graph Transformer
• Graph Convolutions Enrich the Self-Attention in Transformers!
• Transformers need glasses! Information over-squashing in language tasks
• Finding Transformer Circuits With Edge Pruning
• Any2Graph: Deep End-To-End Supervised Graph Prediction With An Optimal Transport Loss
• A Foundation Model for Zero-shot Logical Query Reasoning
• MeshXL: Neural Coordinate Field for Generative 3D Foundation Models
• GFT: Graph Foundation Model with Transferable Tree Vocabulary
• CYCLO: Cyclic Graph Transformer Approach to Multi-Object Relationship Modeling in Aerial Videos
• Knowledge Circuits in Pretrained Transformers
• FairWire: Fair Graph Generation

Diffusion

• What is my quantum computer good for? Quantum capability learning with physics-aware neural networks

Diffusion

• Online Relational Inference for Evolving Multi-agent Interacting Systems
• Can Graph Learning Improve Planning in LLM-based Agents?
• Decision-Making Behavior Evaluation Framework for LLMs under Uncertain Context
• Ad Auctions for LLMs via Retrieval Augmented Generation
• LLM Dataset Inference: Did you train on my dataset?
• LLMs as Zero-shot Graph Learners: Alignment of GNN Representations with LLM Token Embeddings

Diffusion

• Transcoders find interpretable LLM feature circuits
• A hierarchical decomposition for explaining ML performance discrepancies
• RegExplainer: Generating Explanations for Graph Neural Networks in Regression Tasks
• GraphTrail: Translating GNN Predictions into Human-Interpretable Logical Rules
• Interpretable Lightweight Transformer via Unrolling of Learned Graph Smoothness Priors
• MIDGArD: Modular Interpretable Diffusion over Graphs for Articulated Designs

Diffusion

• DECRL: A Deep Evolutionary Clustering Jointed Temporal Knowledge Graph Representation Learning Approach
• State Space Models on Temporal Graphs: A First-Principles Study
• Improving Temporal Link Prediction via Temporal Walk Matrix Projection
• Using Time-Aware Graph Neural Networks to Predict Temporal Centralities in Dynamic Graphs
• Temporal Graph Neural Tangent Kernel with Graphon-Guaranteed
• Learning from Highly Sparse Spatio-temporal Data
• A Motion-aware Spatio-temporal Graph for Video Salient Object Ranking
• EGSST: Event-based Graph Spatiotemporal Sensitive Transformer for Object Detection

Diffusion

• Enhancing Chess Reinforcement Learning with Graph Representation
• Compositional Automata Embeddings for Goal-Conditioned Reinforcement Learning
• Enhancing Robustness of Graph Neural Networks on Social Media with Explainable Inverse Reinforcement Learning
• FlexPlanner: Flexible 3D Floorplanning via Deep Reinforcement Learning in Hybrid Action Space with Multi-Modality Representation
• Optimizing Automatic Differentiation with Deep Reinforcement Learning
• On the Role of Information Structure in Reinforcement Learning for Partially-Observable Sequential Teams and Games
• Integrating Suboptimal Human Knowledge with Hierarchical Reinforcement Learning for Large-Scale Multiagent Systems

Diffusion

• RGFN: Synthesizable Molecular Generation Using GFlowNets

Diffusion

• Differentially Private Graph Diffusion with Applications in Personalized PageRanks
• A Simple and Adaptive Learning Rate for FTRL in Online Learning with Minimax Regret of $\\Theta(T^{2/3})$ and its Application to Best-of-Both-Worlds
• PediatricsGPT: Large Language Models as Chinese Medical Assistants for Pediatric Applications
• A Textbook Remedy for Domain Shifts: Knowledge Priors for Medical Image Analysis
• HEALNet: Multimodal Fusion for Heterogeneous Biomedical Data
• Knowledge-Empowered Dynamic Graph Network for Irregularly Sampled Medical Time Series
• Construction and Application of Materials Knowledge Graph in Multidisciplinary Materials Science via Large Language Model

Diffusion

• FedNE: Surrogate-Assisted Federated Neighbor Embedding for Dimensionality Reduction
• FedGMark: Certifiably Robust Watermarking for Federated Graph Learning
• Federated Graph Learning for Cross-Domain Recommendation
• FedSSP: Federated Graph Learning with Spectral Knowledge and Personalized Preference
• On provable privacy vulnerabilities of graph representations
• Federated Natural Policy Gradient and Actor Critic Methods for Multi-task Reinforcement Learning

Diffusion

• Markov Equivalence and Consistency in Differentiable Structure Learning
• SpatialRGPT: Grounded Spatial Reasoning in Vision-Language Models
• On the Robustness of Spectral Algorithms for Semirandom Stochastic Block Models
• Domain Adaptation for Large-Vocabulary Object Detectors
• Tackling Uncertain Correspondences for Multi-Modal Entity Alignment
• Learning rigid-body simulators over implicit shapes for large-scale scenes and vision
• Combining Observational Data and Language for Species Range Estimation
• GS-Hider: Hiding Messages into 3D Gaussian Splatting
• Buffer of Thoughts: Thought-Augmented Reasoning with Large Language Models
• Instance-Optimal Private Density Estimation in the Wasserstein Distance
• DDGS-CT: Direction-Disentangled Gaussian Splatting for Realistic Volume Rendering
• Evaluating the World Model Implicit in a Generative Model
• Double-Ended Synthesis Planning with Goal-Constrained Bidirectional Search
• Fair Wasserstein Coresets
• Director3D: Real-world Camera Trajectory and 3D Scene Generation from Text
• Delving into the Reversal Curse: How Far Can Large Language Models Generalize?
• DreamMesh4D: Video-to-4D Generation with Sparse-Controlled Gaussian-Mesh Hybrid Representation
• Posture-Informed Muscular Force Learning for Robust Hand Pressure Estimation
• EGonc : Energy-based Open-Set Node Classification with substitute Unknowns
• Practical Shuffle Coding
• Gene-Gene Relationship Modeling Based on Genetic Evidence for Single-Cell RNA-Seq Data Imputation
• Divide-and-Conquer Predictive Coding: a structured Bayesian inference algorithm
• Semi-Random Matrix Completion via Flow-Based Adaptive Reweighting
• Semantic Routing via Autoregressive Modeling
• Divergences between Language Models and Human Brains
• Expected Probabilistic Hierarchies
• If You Want to Be Robust, Be Wary of Initialization
• Accelerating ERM for data-driven algorithm design using output-sensitive techniques
• Towards Flexible Visual Relationship Segmentation
• MKGL: Mastery of a Three-Word Language
• GSDF: 3DGS Meets SDF for Improved Neural Rendering and Reconstruction
• Make-it-Real: Unleashing Large Multimodal Model for Painting 3D Objects with Realistic Materials
• Strategic Littlestone Dimension: Improved Bounds on Online Strategic Classification
• Non-Euclidean Mixture Model for Social Network Embedding
• EEG2Video: Towards Decoding Dynamic Visual Perception from EEG Signals
• PageRank Bandits for Link Prediction
• Deep Homomorphism Networks
• HardCore Generation: Generating Hard UNSAT Problems for Data Augmentation
• Geometry Awakening: Cross-Geometry Learning Exhibits Superiority over Individual Structures
• Sequential Harmful Shift Detection Without Labels
• Dynamic 3D Gaussian Fields for Urban Areas
• Learning to Solve Quadratic Unconstrained Binary Optimization in a Classification Way
• Learning Representations for Hierarchies with Minimal Support
• Amortized Eigendecomposition for Neural Networks
• Transferable Boltzmann Generators
• Upping the Game: How 2D U-Net Skip Connections Flip 3D Segmentation
• UniAR: A Unified model for predicting human Attention and Responses on visual content
• Scaling Continuous Latent Variable Models as Probabilistic Integral Circuits
• Visual Sketchpad: Sketching as a Visual Chain of Thought for Multimodal Language Models
• Deep Equilibrium Algorithmic Reasoning
• From an Image to a Scene: Learning to Imagine the World from a Million 360 Videos
• DMNet: Self-comparison Driven Model for Subject-independent Seizure Detection
• Enhancing Robustness of Last Layer Two-Stage Fair Model Corrections
• Hardness of Learning Neural Networks under the Manifold Hypothesis
• TopoFR: A Closer Look at Topology Alignment on Face Recognition
• IntraMix: Intra-Class Mixup Generation for Accurate Labels and Neighbors
• Neural decoding from stereotactic EEG: accounting for electrode variability across subjects
• UniMTS: Unified Pre-training for Motion Time Series
• HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Models
• eXponential FAmily Dynamical Systems (XFADS): Large-scale nonlinear Gaussian state-space modeling
• Breaking the curse of dimensionality in structured density estimation
• Who Evaluates the Evaluations? Objectively Scoring Text-to-Image Prompt Coherence Metrics with T2IScoreScore (TS2)
• GLinSAT: The General Linear Satisfiability Neural Network Layer By Accelerated Gradient Descent
• The Factorization Curse: Which Tokens You Predict Underlie the Reversal Curse and More
• Synergistic Dual Spatial-aware Generation of Image-to-text and Text-to-image
• Improving Robustness of 3D Point Cloud Recognition from a Fourier Perspective
• On Differentially Private U Statistics
• Towards Estimating Bounds on the Effect of Policies under Unobserved Confounding
• Generative Hierarchical Materials Search
• ChatCam: Empowering Camera Control through Conversational AI
• Injecting Undetectable Backdoors in Obfuscated Neural Networks and Language Models
• Unified Insights: Harnessing Multi-modal Data for Phenotype Imputation via View Decoupling
• Du-IN: Discrete units-guided mask modeling for decoding speech from Intracranial Neural signals
• Estimating Epistemic and Aleatoric Uncertainty with a Single Model
• NeuralSteiner: Learning Steiner Tree for Overflow-avoiding Global Routing in Chip Design
• Consensus Learning with Deep Sets for Essential Matrix Estimation
• Towards Effective Planning Strategies for Dynamic Opinion Networks
• Learning Low-Rank Feature for Thorax Disease Classification
• Smoothie: Label Free Language Model Routing
• SpeAr: A Spectral Approach for Zero-Shot Node Classification
• A robust inlier identification algorithm for point cloud registration via $\\mathbf{\\ell_0}$-minimization
• Metric Space Magnitude for Evaluating the Diversity of Latent Representations
• The Importance of Being Scalable: Improving the Speed and Accuracy of Neural Network Interatomic Potentials Across Chemical Domains
• G3: An Effective and Adaptive Framework for Worldwide Geolocalization Using Large Multi-Modality Models
• Learning Discrete Concepts in Latent Hierarchical Models
• MeMo: Meaningful, Modular Controllers via Noise Injection
• Edit Distance Robust Watermarks via Indexing Pseudorandom Codes
• Neural Network Reparametrization for Accelerated Optimization in Molecular Simulations
• Transfer Learning for Latent Variable Network Models
• Testing Calibration in Nearly-Linear Time
• Collaborative Cognitive Diagnosis with Disentangled Representation Learning for Learner Modeling
• Relational Concept Bottleneck Models
• Navigating Chemical Space with Latent Flows
• Post-Hoc Reversal: Are We Selecting Models Prematurely?
• Geodesic Optimization for Predictive Shift Adaptation on EEG data
• Neural Pfaffians: Solving Many Many-Electron Schrodinger Equations
• Differentiable Structure Learning with Partial Orders
• Taming the Long Tail in Human Mobility Prediction
• CLIP in Mirror: Disentangling text from visual images through reflection
• Multilingual Diversity Improves Vision-Language Representations
• Expert-level protocol translation for self-driving labs
• Wild-GS: Real-Time Novel View Synthesis from Unconstrained Photo Collections
• Generative Forests
• bit2bit: 1-bit quanta video reconstruction via self-supervised photon prediction
• Inversion-based Latent Bayesian Optimization
• ST$_k$: A Scalable Module for Solving Top-k Problems
• DEL: Discrete Element Learner for Learning 3D Particle Dynamics with Neural Rendering
• Counterfactual Fairness by Combining Factual and Counterfactual Predictions
• AUCSeg: AUC-oriented Pixel-level Long-tail Semantic Segmentation
• Iterative Methods via Locally Evolving Set Process
• Can Models Learn Skill Composition from Examples?
• Exponential Quantum Communication Advantage in Distributed Inference and Learning
• DeiSAM: Segment Anything with Deictic Prompting
• Group Robust Preference Optimization in Reward-free RLHF
• Harnessing Multiple Correlated Networks for Exact Community Recovery
• Why the Metric Backbone Preserves Community Structure
• MambaTree: Tree Topology is All You Need in State Space Model
• On the Optimal Time Complexities in Decentralized Stochastic Asynchronous Optimization
• Invariant Tokenization of Crystalline Materials for Language Model Enabled Generation
• Energy-Based Modelling for Discrete and Mixed Data via Heat Equations on Structured Spaces
• Information Re-Organization Improves Reasoning in Large Language Models
• Qualitative Mechanism Independence
• On the Computational Landscape of Replicable Learning
• Persistent Homology for High-dimensional Data Based on Spectral Methods
• Fairness without Harm: An Influence-Guided Active Sampling Approach
• Extracting Training Data from Molecular Pre-trained Models
• Lambda: Learning Matchable Prior For Entity Alignment with Unlabeled Dangling Cases
• LuSh-NeRF: Lighting up and Sharpening NeRFs for Low-light Scenes
• What type of inference is planning?
• Shape analysis for time series
• realSEUDO for real-time calcium imaging analysis
• Normal-GS: 3D Gaussian Splatting with Normal-Involved Rendering
• DRACO: A Denoising-Reconstruction Autoencoder for Cryo-EM
• Exploring Molecular Pretraining Model at Scale
• FactorizePhys: Matrix Factorization for Multidimensional Attention in Remote Physiological Sensing
• Entity Alignment with Noisy Annotations from Large Language Models
• End-to-End Ontology Learning with Large Language Models
• Questioning the Survey Responses of Large Language Models
• Fractal Patterns May Illuminate the Success of Next-Token Prediction
• Mixture of neural fields for heterogeneous reconstruction in cryo-EM
• Large language model validity via enhanced conformal prediction methods
• TreeVI: Reparameterizable Tree-structured Variational Inference for Instance-level Correlation Capturing
• SpGesture: Source-Free Domain-adaptive sEMG-based Gesture Recognition with Jaccard Attentive Spiking Neural Network
• Latent Intrinsics Emerge from Training to Relight
• Effective Rank Analysis and Regularization for Enhanced 3D Gaussian Splatting