Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

Awesome Lists | Featured Topics | Projects

Awesome-Model-Quantization

A list of papers, docs, codes about model quantization. This repo is aimed to provide the info for model quantization research, we are continuously improving the project. Welcome to PR the works (papers, repositories) that are missed by the repo.
https://github.com/Efficient-ML/Awesome-Model-Quantization

Last synced: 4 days ago
JSON representation

  • Papers

    • 2023

      • [Cognitive Neurodynamics - based convolutional neural network.
      • [MMM
      • [NeurIPS
      • [NeurIPS - bit Quantization for Efficient Image Super-Resolution [[code](https://github.com/htqin/QuantSR)]![GitHub Repo stars](https://img.shields.io/github/stars/htqin/QuantSR)
      • [NeurIPS
      • [NeurIPS
      • [NeurIPS - DM: An Efficient Low-bit Quantized Diffusion Model
      • [NeurIPS - Training Quantization for Diffusion Models [[code](https://github.com/ziplab/PTQD)]![GitHub Repo stars](https://img.shields.io/github/stars/ziplab/PTQD)
      • [NeurIPS
      • [NeurIPS - Efficient Fine-Tuning of Compressed Large Language Models via sub-4-bit Integer Quantization
      • [ICML
      • [ICML - wise Division for Post-Training Quantization [[code](https://openreview.net/attachment?id=-tYCaP0phY_&name=supplementary_material)]
      • [ICML
      • [ICML - Zip: Deep Compression of Finetuned Large Language Models
      • [ICML - DASLab/QIGen)]![GitHub Repo stars](https://img.shields.io/github/stars/IST-DASLab/QIGen)
      • [ICML - bit precision: k-bit Inference Scaling Laws
      • [TPAMI - Based Post-Training Quantization With Bit-Split and Stitching
      • [TPAMI - path Bit Sharing for Automatic Loss-aware Model Compression
      • [ICCV - DFQ: Causality Guided Data-free Network Quantization [[code](https://github.com/42Shawn/Causal-DFQ)]![GitHub Repo stars](https://img.shields.io/github/stars/42Shawn/Causal-DFQ)
      • [ICCV - Diffusion: Quantizing Diffusion Models [[code](https://github.com/Xiuyu-Li/q-diffusion)]![GitHub Repo stars](https://img.shields.io/github/stars/Xiuyu-Li/q-diffusion)
      • [ICCV - BEV : Quantization-aware View-guided Distillation for Multi-view 3D Object Detection
      • [arXiv - Efficiency Trade-off of LLM Inference with Transferable Prompt
      • [CVPR - training Quantization on Diffusion Models [[code](https://github.com/42Shawn/PTQ4DM)]![GitHub Repo stars](https://img.shields.io/github/stars/42Shawn/PTQ4DM)
      • [CVPR - DETR: An Efficient Low-Bit Quantized Detection Transformer [[code](https://github.com/SteveTsui/Q-DETR)]![GitHub Repo stars](https://img.shields.io/github/stars/SteveTsui/Q-DETR)
      • [CVPR - Shot Quantization
      • [CVPR - Training Quantization for Image Super Resolution
      • [CVPR - Shot Model for Mixed-Precision Quantization
      • [CVPR - Quant: Post-Training Quantization Based on Prediction Difference Metric [[code](https://github.com/hustvl/PD-Quant)]![GitHub Repo stars](https://img.shields.io/github/stars/hustvl/PD-Quant)
      • [CVPR - Free Quantization
      • [CVPR - Enhanced Post-Training Activation Quantization for Vision Transformers
      • [CVPR - Friendly Sparsity and Quantization
      • [CVPR - based Integrated Pseudo-Quantization
      • [CVPR - shrinking: Limiting Instantaneous Sharpness for Improving Post-training Quantization
      • [CVPR - Training Quantization Through a Theoretical Perspective
      • [CVPR - quantization
      • [CVPR
      • [CVPR
      • [CVPRW - hoan-le/binaryvit)]
      • [ICLR - Conditioning
      • [ACL - agnostic Quantization Approach for Pre-trained Language Models
      • [ACL - based Language Models with GPU-Friendly Sparsity and Quantization
      • [EMNLP - based Quantisation: What is Important for Sub-8-bit LLM Inference?
      • [EMNLP - Shot Sharpness-Aware Quantization for Pre-trained Language Models
      • [EMNLP - FP4: 4-Bit Floating-Point Quantized Transformers [[code](https://github.com/nbasyl/LLM-FP4)]
      • [EMNLP - Watermark)]
      • [EMNLP
      • [TNNLS - Network Performance. [__`bnn`__] [[code](https://github.com/htqin/BiFSMNv2)]
      • [TNNLS
      • [HPCA - Quality Uncertainty Quantification in a PIM Designed for Bayesian Neural Network
      • [TIP - Bitwidth-Fixed, Mixed-Precision Quantization Method for Mobile CNN-Based Applications
      • [TCSVT
      • [WACV
      • [WACV - Free Per-Channel Static Input Quantization
      • [WACV - Teacher Knowledge Distillation for Learning Low Bit-width Deep Neural Networks.
      • [PR
      • [PR - free quantization via mixed-precision compensation without fine-tuning.
      • [NN - range zero-shot generative deep network quantization.
      • [Cognitive Neurodynamics - based convolutional neural network.
      • [MMM
      • [ISCA - friendly Outlier-Victim Pair Quantization
      • [Cognitive Neurodynamics - based convolutional neural network.
      • [MMM
      • [Cognitive Neurodynamics - based convolutional neural network.
      • [MMM
      • [Cognitive Neurodynamics - based convolutional neural network.
      • [MMM
      • [Cognitive Neurodynamics - based convolutional neural network.
      • [MMM
      • [ICCV
      • [Cognitive Neurodynamics - based convolutional neural network.
      • [MMM
      • [MMM
      • [Cognitive Neurodynamics - based convolutional neural network.
      • [Cognitive Neurodynamics - based convolutional neural network.
      • [MMM
      • [Cognitive Neurodynamics - based convolutional neural network.
      • [MMM
      • [MMM
      • [Cognitive Neurodynamics - based convolutional neural network.
      • [MMM
      • [Cognitive Neurodynamics - based convolutional neural network.
      • [MMM
      • [Cognitive Neurodynamics - based convolutional neural network.
      • [Cognitive Neurodynamics - based convolutional neural network.
      • [MMM
      • [Cognitive Neurodynamics - based convolutional neural network.
      • [MMM
      • [Cognitive Neurodynamics - based convolutional neural network.
      • [MMM
      • [TNNLS - Network Performance. [__`bnn`__] [[code](https://github.com/htqin/BiFSMNv2)]
      • [HPCA - Quality Uncertainty Quantification in a PIM Designed for Bayesian Neural Network
      • [Cognitive Neurodynamics - based convolutional neural network.
      • [MMM
      • [Cognitive Neurodynamics - based convolutional neural network.
      • [MMM
      • [Cognitive Neurodynamics - based convolutional neural network.
      • [MMM
      • [Cognitive Neurodynamics - based convolutional neural network.
      • [MMM
      • [Cognitive Neurodynamics - based convolutional neural network.
      • [MMM
      • [Cognitive Neurodynamics - based convolutional neural network.
      • [MMM
      • [arXiv
      • [arXiv
      • [arXiv - training Quantization for Neural Networks with Provable Guarantees.
      • [arXiv - V2: Exploring Post-training Quantization in LLMs from Comprehensive Study to Low Rank Compensation.
      • [arXiv - HyViT: Post-Training Quantization for Hybrid Vision Transformer with Bridge Block Reconstruction.
      • [arXiv - Resolution. [__`bnn`__]
      • [arXiv
      • [arXiv - based Post-training Quantization for Large Language Models. [[code](https://github.com/hahnyuan/RPTQ4LLM)]
      • [arXiv - Training Quantization on Object Detection with Task Loss-Guided Lp Metric. [__`ptq`__]
      • [arXiv - Bit Quantization on Large Language Models.
      • [arXiv - GEMM: Quantized Matrix Multiplication based on LUTs for Efficient Inference in Large-Scale Generative Language Models
      • [arXiv - Quantized Representation for Near-Lossless LLM Weight Compression [[code](https://github.com/Vahe1994/SpQR)]
      • [arXiv
      • [arXiv - QAT: Data-Free Quantization Aware Training for Large Language Models
      • [arXiv - aware Weight Quantization for LLM Compression and Acceleration [[code](https://github.com/mit-han-lab/llm-awq)]
      • [arXiv - bit Integers [[code](https://github.com/xijiu9/Train_Transformers_with_INT4)]
      • [arXiv - free Quantization for Diffusion Models
      • [arXiv - Tunable Quantized Large Language Models with Error Correction through Low-Rank Adaptation
      • [arXiv - and-Sparse Quantization [[code](https://github.com/SqueezeAILab/SqueezeLLM)]
      • [arXiv
      • [arXiv
      • [arXiv - FP-QSim: Mixed Precision and Formats For Large Language Models and Vision Transformers [[code](https://github.com/lightmatter-ai/INT-FP-QSim)]
      • [arXiv - FP: A Leap Forward in LLMs Post-Training W4A8 Quantization Using Floating-Point Formats.
      • [arXiv
      • [arXiv
      • [arXiv - Bit Quantization of Large Language Models With Guarantees. [[code](https://github.com/jerry-chee/QuIP)]
      • [arXiv - Uniform Post-Training Quantization via Power Exponent Search
      • [arXiv - Scaled Logit Distillation for Ternary Weight Generative Language Models
      • [arXiv - Based Post-Training Quantization: Challenging the Status Quo
      • [arXiv - Grained Weight-Only Quantization for LLMs
      • [arXiv
      • [arXiv - VQ: Compression for Tractable Internet-Scale Memory
      • [arXiv - grained Post-Training Quantization for Large Language Models
      • [arXiv - time Weight Clustering for Large Language Models
      • [arXiv - based Quantization for Language Models - An Efficient and Intuitive Algorithm
      • [arXiv - performance Low-bit Quantization of Large Language Models
      • [arXiv - Training Quantization on Large Language Models
      • [arXiv - compressor)]
      • [arXiv - LLM: Partially Binarized Large Language Models. [[code](https://github.com/hahnyuan/PB-LLM)]
      • [arXiv - Diffusion: Vector Quantized Discrete Diffusion Model with Spiking Neural Networks [[code](https://github.com/Arktis2022/Spiking-Diffusion)] [__`snn`__]
      • [arXiv - training Quantization with FP8 Formats [[code](https://github.com/intel/neural-compressor)]
      • [arXiv - LoRA: Quantization-Aware Low-Rank Adaptation of Large Language Models [[code](https://github.com/yuhuixu1993/qa-lora)]
      • [arXiv - bit Weight Quantization of Large Language Models
      • [arXiv - Bit LLMs on Consumer GPUs by Integrating with Modular Quantizers
      • [arXiv - parameter Tuning of LLMs with Affordable Resources
      • [arXiv - Bitwidth Quantization for Large Language Models
      • [arXiv - Fine-Tuning-Aware Quantization for Large Language Models [[code](https://github.com/yxli2123/LoftQ)]
      • [arXiv - compressor)]
      • [arXiv - bit Transformers for Large Language Models [[code](https://github.com/kyegomez/BitNet)]
      • [arXiv - LM: Training FP8 Large Language Models [[code](https://github.com/Azure/MS-AMP)]
      • [arXiv - bit Quantization for Efficient and Accurate LLM Serving [[code](https://github.com/efeslab/Atom)]
      • [arXiv - Training Quantization with Activation-Weight Equalization for Large Language Models
      • [arXiv
      • [Cognitive Neurodynamics - based convolutional neural network.
      • [MMM
      • [Cognitive Neurodynamics - based convolutional neural network.
      • [MMM
      • [Cognitive Neurodynamics - based convolutional neural network.
      • [MMM
      • [Cognitive Neurodynamics - based convolutional neural network.
      • [MMM
      • [Cognitive Neurodynamics - based convolutional neural network.
      • [MMM
      • [Cognitive Neurodynamics - based convolutional neural network.
      • [MMM
      • [Cognitive Neurodynamics - based convolutional neural network.
      • [MMM
      • [ISCA - friendly Outlier-Victim Pair Quantization
      • [Cognitive Neurodynamics - based convolutional neural network.
      • [MMM
      • [Cognitive Neurodynamics - based convolutional neural network.
      • [MMM
      • [Cognitive Neurodynamics - based convolutional neural network.
      • [MMM
      • [Cognitive Neurodynamics - based convolutional neural network.
      • [MMM
      • [Cognitive Neurodynamics - based convolutional neural network.
      • [MMM
      • [Cognitive Neurodynamics - based convolutional neural network.
      • [MMM
      • [Cognitive Neurodynamics - based convolutional neural network.
      • [MMM
      • [Cognitive Neurodynamics - based convolutional neural network.
      • [MMM
      • [Cognitive Neurodynamics - based convolutional neural network.
      • [MMM
      • [Cognitive Neurodynamics - based convolutional neural network.
      • [MMM
      • [Cognitive Neurodynamics - based convolutional neural network.
      • [MMM
      • [Cognitive Neurodynamics - based convolutional neural network.
      • [MMM
      • [Cognitive Neurodynamics - based convolutional neural network.
      • [MMM
      • [Cognitive Neurodynamics - based convolutional neural network.
      • [MMM
      • [Cognitive Neurodynamics - based convolutional neural network.
      • [MMM
      • [ICLR - Training Quantization for Generative Pre-trained Transformers [[code](https://github.com/IST-DASLab/gptq)] [721⭐]
      • [Cognitive Neurodynamics - based convolutional neural network.
      • [MMM
      • [ICML
      • [CVPR - Enhanced Post-Training Activation Quantization for Vision Transformers
      • [CVPR - Training Quantization Through a Theoretical Perspective
      • [Cognitive Neurodynamics - based convolutional neural network.
      • [MMM
      • [arXiv - training Quantization for Neural Networks with Provable Guarantees.
      • [Cognitive Neurodynamics - based convolutional neural network.
      • [MMM
      • [PR - free quantization via mixed-precision compensation without fine-tuning.
      • [NN - range zero-shot generative deep network quantization.
      • [Cognitive Neurodynamics - based convolutional neural network.
      • [MMM
      • [Cognitive Neurodynamics - based convolutional neural network.
      • [MMM
      • [Cognitive Neurodynamics - based convolutional neural network.
      • [MMM
      • [Cognitive Neurodynamics - based convolutional neural network.
      • [MMM
      • [Cognitive Neurodynamics - based convolutional neural network.
      • [MMM

    • 2022

      • [ECCV - Computing-Lab-Yale/NDA_SNN)
      • [ESE - Based Software Testing approach for Deep Neural Network Quantization assessment.
      • [EANN - Aware Training Method for Photonic Neural Networks.
      • [CCF Transactions on High Performance Computing
      • [LNAI - Driven Quantization for Low-Bit and Sparse DNNs.
      • [NeurIPS
      • [NeurIPS
      • [NeurIPS - training Quantization of Pre-trained Language Models. [__`qnn`__]
      • [NeurIPS - Training Quantization and Pruning. [__`qnn`__] [**`hardware`**]
      • [ECCV
      • [ECCV - Computing-Lab-Yale/NDA_SNN)
      • [IJCV - sensitive Information Retention for Accurate Binary Neural Network. [__`bnn`__]
      • [ICML
      • [ICML - Optimal Low-Bit Sub-Distribution in Deep Neural Networks [**`qnn`**] [**`hardware`**]
      • [ICML
      • [ICLR
      • [CVPR - SNN: Rectifying Membrane Potential Distribution for Directly Training Spiking Neural Networks. [**`snn`**]
      • [CVPR - Shot Quantization Brought Closer to the Teacher. [**`qnn`**] [[code](https://github.com/iamkanghyunchoi/ait)]
      • [CVPR - Free Network Compression via Parametric Non-uniform Mixed Precision Quantization. [__`qnn`__]
      • [CVPR
      • [CVPR - Aware Dynamic Neural Network Quantization. [__`qnn`__]
      • [NeurIPS - distilled Transformer. [**`bnn`**] [[code](https://github.com/facebookresearch/bit)] [42⭐]
      • [NeurIPS - Layer Dependency for Post -Training Quantization. [__`qnn`__]
      • [NeurIPS - Aware Quantization Techniques. [__`qnn`__]
      • [NeurIPS - Driven Mixed-Precision Quantization for Deep Network Design. [__`qnn`__]
      • [NeurIPS - Training Quantization for Large-Scale Transformers. [__`qnn`__]
      • [NeurIPS
      • [NeurIPS - ViT: Accurate and Fully Quantized Low-bit Vision Transformer. [__`qnn`__]
      • [NeurIPS - Layer Perceptrons. [**`bnn`**] [[code](https://gitee.com/mindspore/models/tree/master/research/cv/BiMLP)]
      • [ECCV - Uniform Step Size Quantization for Accurate Post-Training Quantization. [__`qnn`__]
      • [ECCV - Training Quantization for Vision Transformers with Twin Uniform Quantization. [__`qnn`__]
      • [ECCV
      • [ECCV - wise Activation-clipping Search Quantization for Sub-4-bit Neural Networks. [__`qnn`__]
      • [ECCV - Q: Extremely Fine-Grained Channel-Wise Quantization via Rate-Distortion Optimization. [__`qnn`__]
      • [ECCV - Precision Neural Network Quantization via Learned Layer-Wise Importance. [__`qnn`__] [[Code](https://github.com/1hunters/LIMPQ)]
      • [ECCV
      • [ECCV - Free Quantization for Vision Transformers. [__`qnn`__]
      • [IJCAI
      • [IJCAI - of-Two Low-bit Post-training Quantization. [__`qnn`__]
      • [IJCAI - bit Quantization of Neural Networks. [__`qnn`__]
      • [IJCAI - ViT: Post-Training Quantization for Fully Quantized Vision Transformer. [__`qnn`__] [[code](https://github.com/megvii-research/FQ-ViT)] [71:star:]
      • [ICLR - Point 8-bit Only Multiplication for Network Quantization. [**`qnn`**]
      • [ICLR - bit Optimizers via Block-wise Quantization. [**`qnn`**]
      • [ICLR - Precision Training: Data Format Optimization and Hysteresis Quantization. [**`qnn`**]
      • [ICLR
      • [ICLR - the-Fly Data-Free Quantization via Diagonal Hessian Approximation. [**`qnn`**][code](https://github.com/clevercool/SQuant)]
      • [ICLR
      • [TGARS - Based Hyperspectral Image Classification by Step Activation Quantization [__`qnn`__]
      • [arxiv
      • [IJNS
      • [ACM Trans. Des. Autom. Electron. Syst.
      • [MICRO - bit Deep Neural Network Quantization.
      • [ESE - Based Software Testing approach for Deep Neural Network Quantization assessment.
      • [TODAES - in-Memory Neural Networks Acceleration.
      • [CVPR - System-Software-and-Security/BppAttack)]
      • [IEEE Internet of Things Journal - Efficient Federated Learning Framework for IoT With Low-Bitwidth Neural Network Quantization.
      • [FPGA - QNN: Efficient FPGA Acceleration of Deep Neural Networks with Intra-Layer, Mixed-Precision Quantization.
      • [Neural Networks - aware training for low precision photonic neural networks.
      • [ICCRD
      • [Electronics
      • [Applied Soft Computing - distillation and parameter quantization for the bearing fault diagnosis.
      • [CVPR - Class Heterogeneity for Zero-Shot Network Quantization. [[torch](https://github.com/zysxmu/IntraQ)]
      • [Neurocomputing
      • [tinyML Research Symposium - of-Two Quantization for Low Bitwidth and Hardware Compliant Neural Networks.
      • [arXiv - 8-Bit Quantization Aware Training for 8-Bit Neural Network Accelerator with On-Device Speech Recognition.
      • [Ocean Engineering
      • [CVPR - of-Flight Depth Maps.
      • [PPoPP
      • [TCSVT - Q Quantization on FPGA.
      • [EANN - Aware Training Method for Photonic Neural Networks.
      • [arXiv - Precision Quantized Neural Networks.
      • [arXiv
      • [ITSM - Powered Parking Surveillance With Quantized Neural Networks.
      • [Intelligent Automation & Soft Computing - Efficient Convolutional Neural Network Accelerator Using Fine-Grained Logarithmic Quantization.
      • [ICML - Aware Training. [[torch](https://github.com/qualcomm-ai-research/oscillations-qat)]
      • [CCF Transactions on High Performance Computing
      • [CVPR
      • [LNAI - Driven Quantization for Low-Bit and Sparse DNNs.
      • [TCCN - Bitwidth Convolutional Neural Networks for Wireless Interference Identification.
      • [ASE - based Formal Verification Approach for Quantized Neural Networks.
      • [ICPR - Wise Data-Free CNN Compression.
      • [IJCNN - Based Quantized Neural Networks.
      • [NeurIPS - bit Transformer Language Models. [[code](https://github.com/wimh966/outlier_suppression)]
      • [ACL - trained Language Models via Quantization
      • [NeurIPS - bit Matrix Multiplication for Transformers at Scale
      • [Neurocomputing
      • [ECCV - Computing-Lab-Yale/NDA_SNN)
      • [ESE - Based Software Testing approach for Deep Neural Network Quantization assessment.
      • [ECCV - Computing-Lab-Yale/NDA_SNN)
      • [ESE - Based Software Testing approach for Deep Neural Network Quantization assessment.
      • [EANN - Aware Training Method for Photonic Neural Networks.
      • [CCF Transactions on High Performance Computing
      • [LNAI - Driven Quantization for Low-Bit and Sparse DNNs.
      • [ECCV - Computing-Lab-Yale/NDA_SNN)
      • [ESE - Based Software Testing approach for Deep Neural Network Quantization assessment.
      • [EANN - Aware Training Method for Photonic Neural Networks.
      • [CCF Transactions on High Performance Computing
      • [LNAI - Driven Quantization for Low-Bit and Sparse DNNs.
      • [ECCV - Computing-Lab-Yale/NDA_SNN)
      • [ESE - Based Software Testing approach for Deep Neural Network Quantization assessment.
      • [EANN - Aware Training Method for Photonic Neural Networks.
      • [CCF Transactions on High Performance Computing
      • [LNAI - Driven Quantization for Low-Bit and Sparse DNNs.
      • [EANN - Aware Training Method for Photonic Neural Networks.
      • [CCF Transactions on High Performance Computing
      • [LNAI - Driven Quantization for Low-Bit and Sparse DNNs.
      • [ECCV - Computing-Lab-Yale/NDA_SNN)
      • [ESE - Based Software Testing approach for Deep Neural Network Quantization assessment.
      • [ECCV - Computing-Lab-Yale/NDA_SNN)
      • [ESE - Based Software Testing approach for Deep Neural Network Quantization assessment.
      • [EANN - Aware Training Method for Photonic Neural Networks.
      • [CCF Transactions on High Performance Computing
      • [LNAI - Driven Quantization for Low-Bit and Sparse DNNs.
      • [ECCV - Computing-Lab-Yale/NDA_SNN)
      • [ESE - Based Software Testing approach for Deep Neural Network Quantization assessment.
      • [EANN - Aware Training Method for Photonic Neural Networks.
      • [CCF Transactions on High Performance Computing
      • [LNAI - Driven Quantization for Low-Bit and Sparse DNNs.
      • [ECCV - Computing-Lab-Yale/NDA_SNN)
      • [ESE - Based Software Testing approach for Deep Neural Network Quantization assessment.
      • [ECCV - Computing-Lab-Yale/NDA_SNN)
      • [ESE - Based Software Testing approach for Deep Neural Network Quantization assessment.
      • [ECCV - Computing-Lab-Yale/NDA_SNN)
      • [ESE - Based Software Testing approach for Deep Neural Network Quantization assessment.
      • [EANN - Aware Training Method for Photonic Neural Networks.
      • [CCF Transactions on High Performance Computing
      • [LNAI - Driven Quantization for Low-Bit and Sparse DNNs.
      • [ECCV - Computing-Lab-Yale/NDA_SNN)
      • [ESE - Based Software Testing approach for Deep Neural Network Quantization assessment.
      • [EANN - Aware Training Method for Photonic Neural Networks.
      • [CCF Transactions on High Performance Computing
      • [LNAI - Driven Quantization for Low-Bit and Sparse DNNs.
      • [ECCV - Computing-Lab-Yale/NDA_SNN)
      • [arXiv - ViT: Fully Differentiable Quantization for Vision Transformer [__`qnn`__]
      • [arXiv - training Quantization of Convolutional Neural Networks using Extreme Gradient Boosting for Fast Deployment [__`qnn`__]
      • [ESE - Based Software Testing approach for Deep Neural Network Quantization assessment.
      • [tinyML Research Symposium - of-Two Quantization for Low Bitwidth and Hardware Compliant Neural Networks.
      • [EANN - Aware Training Method for Photonic Neural Networks.
      • [ECCV - Computing-Lab-Yale/NDA_SNN)
      • [ESE - Based Software Testing approach for Deep Neural Network Quantization assessment.
      • [CCF Transactions on High Performance Computing
      • [LNAI - Driven Quantization for Low-Bit and Sparse DNNs.
      • [ESE - Based Software Testing approach for Deep Neural Network Quantization assessment.
      • [EANN - Aware Training Method for Photonic Neural Networks.
      • [ECCV - Computing-Lab-Yale/NDA_SNN)
      • [ESE - Based Software Testing approach for Deep Neural Network Quantization assessment.
      • [CVPR - System-Software-and-Security/BppAttack)]
      • [LNAI - Driven Quantization for Low-Bit and Sparse DNNs.
      • [CCF Transactions on High Performance Computing
      • [ECCV - Computing-Lab-Yale/NDA_SNN)
      • [ESE - Based Software Testing approach for Deep Neural Network Quantization assessment.
      • [ESE - Based Software Testing approach for Deep Neural Network Quantization assessment.
      • [ECCV - Computing-Lab-Yale/NDA_SNN)
      • [ESE - Based Software Testing approach for Deep Neural Network Quantization assessment.
      • [EANN - Aware Training Method for Photonic Neural Networks.
      • [CCF Transactions on High Performance Computing
      • [LNAI - Driven Quantization for Low-Bit and Sparse DNNs.
      • [CCF Transactions on High Performance Computing
      • [LNAI - Driven Quantization for Low-Bit and Sparse DNNs.
      • [ESE - Based Software Testing approach for Deep Neural Network Quantization assessment.
      • [ECCV - Computing-Lab-Yale/NDA_SNN)
      • [ESE - Based Software Testing approach for Deep Neural Network Quantization assessment.
      • [EANN - Aware Training Method for Photonic Neural Networks.
      • [CCF Transactions on High Performance Computing
      • [LNAI - Driven Quantization for Low-Bit and Sparse DNNs.
      • [EANN - Aware Training Method for Photonic Neural Networks.
      • [ECCV - Computing-Lab-Yale/NDA_SNN)
      • [ESE - Based Software Testing approach for Deep Neural Network Quantization assessment.
      • [EANN - Aware Training Method for Photonic Neural Networks.
      • [CCF Transactions on High Performance Computing
      • [LNAI - Driven Quantization for Low-Bit and Sparse DNNs.
      • [ECCV - Computing-Lab-Yale/NDA_SNN)
      • [ESE - Based Software Testing approach for Deep Neural Network Quantization assessment.
      • [ECCV - Computing-Lab-Yale/NDA_SNN)
      • [ESE - Based Software Testing approach for Deep Neural Network Quantization assessment.
      • [EANN - Aware Training Method for Photonic Neural Networks.
      • [CCF Transactions on High Performance Computing
      • [LNAI - Driven Quantization for Low-Bit and Sparse DNNs.
      • [ESE - Based Software Testing approach for Deep Neural Network Quantization assessment.
      • [EANN - Aware Training Method for Photonic Neural Networks.
      • [CCF Transactions on High Performance Computing
      • [LNAI - Driven Quantization for Low-Bit and Sparse DNNs.
      • [arXiv - ViT: Fully Differentiable Quantization for Vision Transformer [__`qnn`__]
      • [arXiv - training Quantization of Convolutional Neural Networks using Extreme Gradient Boosting for Fast Deployment [__`qnn`__]
      • [ESE - Based Software Testing approach for Deep Neural Network Quantization assessment.
      • [ECCV - Computing-Lab-Yale/NDA_SNN)
      • [ESE - Based Software Testing approach for Deep Neural Network Quantization assessment.
      • [ECCV - Computing-Lab-Yale/NDA_SNN)
      • [ESE - Based Software Testing approach for Deep Neural Network Quantization assessment.
      • [ECCV - Computing-Lab-Yale/NDA_SNN)
      • [ESE - Based Software Testing approach for Deep Neural Network Quantization assessment.
      • [EANN - Aware Training Method for Photonic Neural Networks.
      • [CCF Transactions on High Performance Computing
      • [LNAI - Driven Quantization for Low-Bit and Sparse DNNs.
      • [CCF Transactions on High Performance Computing
      • [LNAI - Driven Quantization for Low-Bit and Sparse DNNs.
      • [EANN - Aware Training Method for Photonic Neural Networks.
      • [ESE - Based Software Testing approach for Deep Neural Network Quantization assessment.
      • [EANN - Aware Training Method for Photonic Neural Networks.
      • [CCF Transactions on High Performance Computing
      • [LNAI - Driven Quantization for Low-Bit and Sparse DNNs.
      • [ECCV - Computing-Lab-Yale/NDA_SNN)
      • [ESE - Based Software Testing approach for Deep Neural Network Quantization assessment.
      • [ESE - Based Software Testing approach for Deep Neural Network Quantization assessment.
      • [EANN - Aware Training Method for Photonic Neural Networks.
      • [ECCV - Computing-Lab-Yale/NDA_SNN)
      • [ICLR - SNN Conversion for High-accuracy and Ultra-low-latency Spiking Neural Networks. [**`snn`**]
      • [ESE - Based Software Testing approach for Deep Neural Network Quantization assessment.
      • [ECCV - Computing-Lab-Yale/NDA_SNN)
      • [ECCV - Computing-Lab-Yale/NDA_SNN)
      • [ESE - Based Software Testing approach for Deep Neural Network Quantization assessment.
      • [TODAES - in-Memory Neural Networks Acceleration.
      • [FPGA - QNN: Efficient FPGA Acceleration of Deep Neural Networks with Intra-Layer, Mixed-Precision Quantization.
      • [ECCV - Computing-Lab-Yale/NDA_SNN)
      • [ESE - Based Software Testing approach for Deep Neural Network Quantization assessment.
      • [ESE - Based Software Testing approach for Deep Neural Network Quantization assessment.
      • [EANN - Aware Training Method for Photonic Neural Networks.
      • [CCF Transactions on High Performance Computing
      • [LNAI - Driven Quantization for Low-Bit and Sparse DNNs.
      • [ESE - Based Software Testing approach for Deep Neural Network Quantization assessment.
      • [ESE - Based Software Testing approach for Deep Neural Network Quantization assessment.
      • [EANN - Aware Training Method for Photonic Neural Networks.
      • [LNAI - Driven Quantization for Low-Bit and Sparse DNNs.
      • [CCF Transactions on High Performance Computing
      • [ECCV - Computing-Lab-Yale/NDA_SNN)
      • [CVPR - Training Non-Uniform Quantization based on Minimizing the Reconstruction Error. [__`qnn`__]
      • [ESE - Based Software Testing approach for Deep Neural Network Quantization assessment.
      • [EANN - Aware Training Method for Photonic Neural Networks.
      • [CCF Transactions on High Performance Computing
      • [LNAI - Driven Quantization for Low-Bit and Sparse DNNs.
      • [ECCV - Computing-Lab-Yale/NDA_SNN)
      • [ESE - Based Software Testing approach for Deep Neural Network Quantization assessment.
      • [ECCV - Computing-Lab-Yale/NDA_SNN)
      • [ESE - Based Software Testing approach for Deep Neural Network Quantization assessment.
      • [PPoPP
      • [EANN - Aware Training Method for Photonic Neural Networks.
      • [CCF Transactions on High Performance Computing
      • [LNAI - Driven Quantization for Low-Bit and Sparse DNNs.
      • [ECCV - Computing-Lab-Yale/NDA_SNN)
      • [ESE - Based Software Testing approach for Deep Neural Network Quantization assessment.
      • [EANN - Aware Training Method for Photonic Neural Networks.
      • [CCF Transactions on High Performance Computing
      • [LNAI - Driven Quantization for Low-Bit and Sparse DNNs.
      • [ESE - Based Software Testing approach for Deep Neural Network Quantization assessment.
      • [EANN - Aware Training Method for Photonic Neural Networks.
      • [CCF Transactions on High Performance Computing
      • [LNAI - Driven Quantization for Low-Bit and Sparse DNNs.
      • [ECCV - Computing-Lab-Yale/NDA_SNN)
      • [ESE - Based Software Testing approach for Deep Neural Network Quantization assessment.
      • [EANN - Aware Training Method for Photonic Neural Networks.
      • [CCF Transactions on High Performance Computing
      • [LNAI - Driven Quantization for Low-Bit and Sparse DNNs.
      • [ECCV - Computing-Lab-Yale/NDA_SNN)
      • [ESE - Based Software Testing approach for Deep Neural Network Quantization assessment.
      • [EANN - Aware Training Method for Photonic Neural Networks.
      • [CCF Transactions on High Performance Computing
      • [LNAI - Driven Quantization for Low-Bit and Sparse DNNs.
      • [ECCV - Computing-Lab-Yale/NDA_SNN)
      • [ESE - Based Software Testing approach for Deep Neural Network Quantization assessment.
      • [ECCV - Computing-Lab-Yale/NDA_SNN)
      • [ESE - Based Software Testing approach for Deep Neural Network Quantization assessment.
      • [ECCV - Computing-Lab-Yale/NDA_SNN)
      • [ESE - Based Software Testing approach for Deep Neural Network Quantization assessment.
      • [arXiv - Training Quantization for Large Language Models [__`qnn`__] [[code](https://github.com/mit-han-lab/smoothquant)] [150:star:]
      • [ECCV - Computing-Lab-Yale/NDA_SNN)
      • [ESE - Based Software Testing approach for Deep Neural Network Quantization assessment.
      • [ECCV - Computing-Lab-Yale/NDA_SNN)
      • [ESE - Based Software Testing approach for Deep Neural Network Quantization assessment.
      • [ECCV - Computing-Lab-Yale/NDA_SNN)
      • [CVPR - to-Uniform Quantization: Towards Accurate Quantization via Generalized Straight-Through Estimation. [__`qnn`__]
      • [ESE - Based Software Testing approach for Deep Neural Network Quantization assessment.
      • [EANN - Aware Training Method for Photonic Neural Networks.
      • [CCF Transactions on High Performance Computing
      • [LNAI - Driven Quantization for Low-Bit and Sparse DNNs.
      • [ECCV - Computing-Lab-Yale/NDA_SNN)
      • [ESE - Based Software Testing approach for Deep Neural Network Quantization assessment.
      • [EANN - Aware Training Method for Photonic Neural Networks.
      • [CCF Transactions on High Performance Computing
      • [LNAI - Driven Quantization for Low-Bit and Sparse DNNs.
      • [ECCV - Computing-Lab-Yale/NDA_SNN)
      • [ECCV - Computing-Lab-Yale/NDA_SNN)
      • [ESE - Based Software Testing approach for Deep Neural Network Quantization assessment.
      • [ECCV - Computing-Lab-Yale/NDA_SNN)
      • [arXiv
      • [ESE - Based Software Testing approach for Deep Neural Network Quantization assessment.
      • [LNAI - Driven Quantization for Low-Bit and Sparse DNNs.
      • [EANN - Aware Training Method for Photonic Neural Networks.
      • [CCF Transactions on High Performance Computing
      • [IJNS
      • [ESE - Based Software Testing approach for Deep Neural Network Quantization assessment.
      • [ECCV - Computing-Lab-Yale/NDA_SNN)
      • [ESE - Based Software Testing approach for Deep Neural Network Quantization assessment.
      • [ESE - Based Software Testing approach for Deep Neural Network Quantization assessment.
      • [EANN - Aware Training Method for Photonic Neural Networks.
      • [ESE - Based Software Testing approach for Deep Neural Network Quantization assessment.
      • [EANN - Aware Training Method for Photonic Neural Networks.
      • [CCF Transactions on High Performance Computing
      • [LNAI - Driven Quantization for Low-Bit and Sparse DNNs.
      • [ASE - based Formal Verification Approach for Quantized Neural Networks.
      • [Applied Soft Computing - distillation and parameter quantization for the bearing fault diagnosis.
      • [ECCV - Computing-Lab-Yale/NDA_SNN)
      • [ESE - Based Software Testing approach for Deep Neural Network Quantization assessment.
      • [Neural Networks - aware training for low precision photonic neural networks.
      • [ESE - Based Software Testing approach for Deep Neural Network Quantization assessment.
      • [EANN - Aware Training Method for Photonic Neural Networks.
      • [CCF Transactions on High Performance Computing
      • [LNAI - Driven Quantization for Low-Bit and Sparse DNNs.
      • [ECCV - Computing-Lab-Yale/NDA_SNN)
      • [ESE - Based Software Testing approach for Deep Neural Network Quantization assessment.
      • [ESE - Based Software Testing approach for Deep Neural Network Quantization assessment.
      • [ESE - Based Software Testing approach for Deep Neural Network Quantization assessment.
      • [ECCV - Computing-Lab-Yale/NDA_SNN)
      • [ESE - Based Software Testing approach for Deep Neural Network Quantization assessment.
      • [ESE - Based Software Testing approach for Deep Neural Network Quantization assessment.
      • [EANN - Aware Training Method for Photonic Neural Networks.
      • [CCF Transactions on High Performance Computing
      • [LNAI - Driven Quantization for Low-Bit and Sparse DNNs.
      • [ECCV - Computing-Lab-Yale/NDA_SNN)
      • [ESE - Based Software Testing approach for Deep Neural Network Quantization assessment.
      • [ESE - Based Software Testing approach for Deep Neural Network Quantization assessment.
      • [EANN - Aware Training Method for Photonic Neural Networks.
      • [CCF Transactions on High Performance Computing
      • [LNAI - Driven Quantization for Low-Bit and Sparse DNNs.
      • [arXiv - Training Quantization for Large Language Models [__`qnn`__] [[code](https://github.com/mit-han-lab/smoothquant)] [150:star:]
      • [ESE - Based Software Testing approach for Deep Neural Network Quantization assessment.
      • [EANN - Aware Training Method for Photonic Neural Networks.
      • [CCF Transactions on High Performance Computing
      • [LNAI - Driven Quantization for Low-Bit and Sparse DNNs.
      • [ESE - Based Software Testing approach for Deep Neural Network Quantization assessment.
      • [EANN - Aware Training Method for Photonic Neural Networks.
      • [CCF Transactions on High Performance Computing
      • [LNAI - Driven Quantization for Low-Bit and Sparse DNNs.
      • [ESE - Based Software Testing approach for Deep Neural Network Quantization assessment.
      • [EANN - Aware Training Method for Photonic Neural Networks.
      • [CCF Transactions on High Performance Computing
      • [LNAI - Driven Quantization for Low-Bit and Sparse DNNs.
      • [ESE - Based Software Testing approach for Deep Neural Network Quantization assessment.
      • [EANN - Aware Training Method for Photonic Neural Networks.
      • [CCF Transactions on High Performance Computing
      • [LNAI - Driven Quantization for Low-Bit and Sparse DNNs.
      • [ECCV - Computing-Lab-Yale/NDA_SNN)
      • [ESE - Based Software Testing approach for Deep Neural Network Quantization assessment.

    • 2021

      • [AAAI
      • [ICLR
      • [ICML
      • [ICML - Bit Activation Compressed Training [**`qnn`**]
      • [ICML - V3: Dyadic Neural Network Quantization. [**`qnn`**]
      • [ICML - BERT: Integer-only BERT Quantization. [**`qnn`**]
      • [ICML
      • [ICML - NBA: Efficient and Effective Search Over the Joint Space of Networks, Bitwidths, and Accelerators. [**`qnn`**]
      • [ICCV - Free Compression Are Feature and Data Mixing.
      • [CVPR - bnn: Bridging the gap between self-supervised real and 1-bit neural networks via guided distribution calibration [**`bnn`**] [[code](https://github.com/szq0214/S2-BNN)] [52⭐]
      • [CVPR - Free Quantization. [__`qnn`__]
      • [ACM MM - hops Graph Reasoning for Explicit Representation Learning. [__`other`__]
      • [ACM MM - Resolution Networks. [**`qnn`**]
      • [NeurIPS - free Quantization with Synthetic Boundary Supporting Samples. [__`qnn`__]
      • [NeurIPS - Training Quantization for Vision Transformer. [__`mixed`__]
      • [NeurIPS - Training Sparsity-Aware Quantization. [__`qnn`__]
      • [NeurIPS
      • [NeurIPS - GNN: A Universal Framework to Scale up Graph Neural Networks using Vector Quantization. [__`other`__]
      • [NeurIPS - ANTI-zation: Exploiting Quantization Artifacts for Achieving Adversarial Outcomes .
      • [NeurIPS - of-Distribution Robustness. [**`bnn`**] [[torch](https://github.com/chrundle/biprop)]
      • [CVPR - bit Neural Networks. [__`qnn`__]
      • [CVPR - shot Adversarial Quantization. [__`qnn`__] [[torch](https://github.com/FLHonker/ZAQ-code)]
      • [CVPR
      • [CVPR - wise Gradient Scaling. [__`qnn`__] [[torch](https://github.com/cvlab-yonsei/EWGS)]
      • [CVPR
      • [ICLR
      • [ICLR - Capacity Expert Binary Networks. [**`bnn`**]
      • [ICLR - Prize Lottery Ticket Hypothesis: Finding Accurate Binary Neural Networks by Pruning A Randomly Weighted Network. [**`bnn`**]
      • [ICLR - Training Quantization by Block Reconstruction. [__`qnn`__] [[torch](https://github.com/yhhhli/BRECQ)]
      • [ICLR - lognormal: improved quantized and sparse training. [__`qnn`__]
      • [ICLR
      • [ICLR - shot learning via vector quantization in deep embedded space. [__`qnn`__]
      • [ICLR - Quant: Quantization-Aware Training for Graph Neural Networks. [__`qnn`__]
      • [ICLR - Level Sparsity for Mixed-Precision Neural Network Quantization. [__`qnn`__]
      • [ICLR
      • [ICLR
      • [ICLR - Low-Resolution Arithmetic. [__`qnn`__]
      • [ECCV - Resolution via Parameterized Max Scale. [__`qnn`__]
      • [AAAI
      • [AAAI
      • [AAAI - Precision Activation Quantization. [__`qnn`__]
      • [AAAI - shot Pruning-Quantization. [__`qnn`__]
      • [AAAI
      • [AAAI
      • [AAAI - Widths. [__`qnn`__]
      • [AAAI - ­‐training Quantization with Multiple Points: Mixed Precision without Mixed Precision. [__`qnn`__]
      • [AAAI
      • [AAAI - Efficient Kernel SVM via Binary Embedding and Ternary Coefficients. [**`bnn`**]
      • [AAAI - ­Dimensional Binary Convolution Filters. [**`bnn`**]
      • [ACL - time Quantization of Attention Values in Transformers. [__`qnn`__]
      • [ACM MM - hops Graph Reasoning for Explicit Representation Learning. [__`other`__]
      • [AAAI
      • [AAAI - ­‐training Quantization with Multiple Points: Mixed Precision without Mixed Precision. [__`qnn`__]
      • [AAAI
      • [AAAI - Efficient Kernel SVM via Binary Embedding and Ternary Coefficients. [**`bnn`**]
      • [AAAI - ­Dimensional Binary Convolution Filters. [**`bnn`**]
      • [arXiv - Precision Deep Neural Networks. [__`mixed`__] [[torch](https://github.com/SHI-Labs/Any-Precision-DNNs)]
      • [arXiv - hXu/ReCU)]
      • [arXiv - Training Quantization for Vision Transformer. [**`qnn`**]
      • [arXiv
      • [arXiv
      • [CVPR - tune: Efficient Compression of Neural Networks. [__`qnn`__] [[torch](https://github.com/uber-research/permute-quantize-finetune)] [137⭐]

    • 2020

      • [CVPR - Net)] [105:star:] <!--citation 15-->
      • [ACL - -citation 0-->
      • [AAAI
      • [AAAI - BERT: Hessian Based Ultra Low Precision Quantization of BERT. [__`qnn`__]
      • [AAAI - Inducing Binarized Neural Networks. [**`bnn`**]
      • [AAAI - Width Quantization with Multiple Phase Adaptations.
      • [COOL CHIPS - DRAM Accelerator Architecture for Binary Neural Network. [**`hardware`**] <!--citation 0-->
      • [CoRR
      • [CVPR - noah/ghostnet)] [1.2k:star:] <!--citation 47-->
      • [CVPR - han-lab/apq)] [76:star:]
      • [CVPR - Bit Face Recognition. [__`qnn`__]
      • [CVPR - -citation 3-->
      • [CVPR - Point Back-Propagation Training. [[video](https://www.youtube.com/watch?v=nVRNygIQKI0)] [__`qnn`__]
      • [CVPR - Bit Quantization Needs Good Distribution. [**`qnn`**] <!--citation 1-->
      • [ICML - bit quantization through learnable offsets and better initialization
      • [DATE - based computing systems. [**`bnn`**] <!--citation 1-->
      • [DATE - Accelerated Binary Neural Network Inference Engine for Mobile Phones. [**`bnn`**] [**`hardware`**]
      • [DATE - -citation 2-->
      • [ECCV - -citation 5-->
      • [ECCV - 4-bit MobileNet Models. [**`qnn`**] <!--citation 2-->
      • [ECCV - -citation 2-->
      • [ECCV - -citation 7-->
      • [ECCV - -citation 6-->
      • [ECCV - bitwidth Data Free Quantization. [**`qnn`**] [[torch](https://github.com/xushoukai/GDFQ)]
      • [EMNLP - aware Ultra-low Bit BERT. [**`qnn`**]
      • [EMNLP
      • [ICET - Efficient Bagged Binary Neural Network Accelerator. [**`bnn`**] [**`hardware`**] <!--citation 0-->
      • [ICASSP - -citation 3-->
      • [ICML - -citation 5-->
      • [ICML - Scale Inference with Anisotropic Vector Quantization.
      • [ICLR
      • [ICLR - to-Binary Convolutions. [**`bnn`**] [[code is comming](https://github.com/brais-martinez/real2binary)] [[re-implement](https://github.com/larq/zoo/blob/master/larq_zoo/literature/real_to_bin_nets.py)] <!--citation 19-->
      • [ICLR - K1m/BinaryDuo)] <!--citation 6-->
      • [ICLR - research-code/tree/master/mixed-precision-dnns)] [73:star:]
      • [ICLR
      • [IJCV - -citation 0-->
      • [IJCAI - NAS: Child-Parent Neural Architecture Search for Binary Neural Networks. [**`bnn`**]
      • [IJCAI - bit Integer Inference for the Transformer Model. [**`qnn`**] [**`nlp`**]
      • [IJCAI
      • [IJCAI - bit Multiply-Accumulate Operations. [**`qnn`**]
      • [IJCAI - width Deep Neural Networks. [**`qnn`**]
      • [IJCAI
      • [ISCAS - Level Binarized Recurrent Neural Network for EEG Signal Classification. [**`bnn`**] <!--citation 0-->
      • [ISQED - ASU/BNNPruning)] <!--citation 0-->
      • [MICRO - Based NLP Models for Low Latency and Energy Efficient Inference. [**`qnn`**] [**`nlp`**]
      • [MLST - -citation 11-->
      • [NeurIPS
      • [NeurIPS - Bit Weights in Quantized Neural Networks. [**`qnn`**] [[torch](https://github.com/zhaohui-yang/Binary-Neural-Networks/tree/main/SLB)] <!--citation 4-->
      • [NeurIPS
      • [NeurIPS - kai/eevbnn)]
      • [NeurIPS - Analytic Gradient Estimators for Stochastic Binary Networks. [**`bnn`**] [[code](https://github.com/shekhovt/PSA-Neurips2020)]
      • [NeurIPS - V2: Hessian Aware trace-Weighted Quantization of Neural Networks. [**`qnn`**]
      • [NeurIPS
      • [NeurIPS
      • [NeurIPS - Layer Flow. [**`qnn`**] [[torch](https://github.com/didriknielsen/pixelcnn_flow)]
      • [NeurIPS - Parallel SGD. [**`qnn`**] [[torch](https://github.com/tabrizian/learning-to-quantize)]
      • [NeurIPS
      • [NeurIPS - based Scaled Gradient for Model Quantization and Pruning. [**`qnn`**] [[torch](https://github.com/Jangho-Kim/PSG-pytorch)]
      • [NN - performance and large-scale deep neural networks with full 8-bit integers. [**`qnn`**] <!--citation 13-->
      • [Neurocomputing
      • [PR Letters - -citation 0-->
      • [SysML - to-End Binarized Neural Networks. [**`qnn`**] [[tensorflow](https://github.com/jwfromm/Riptide)] [129:star:] <!--citation 5-->
      • [TPAMI - cnn-landmarks)] [[code](https://github.com/1adrianb/binary-human-pose-estimation)]
      • [TPAMI - Nets: A Coupled and Quantized Approach.
      • [TVLSI - Precision Floating-Point Quantization Oriented Architecture for Convolutional Neural Networks. [**`qnn`**] <!--citation 0-->
      • [WACV - -citation 11-->
      • [IEEE Access - Efficient and High Throughput in-Memory Computing Bit-Cell With Excellent Robustness Under Process Variations for Binary Neural Network. [**`bnn`**] [**`hardware`**] <!--citation 0-->
      • [IEEE Trans. Magn - Memory Binary Neural Network Accelerator. [**`bnn`**] <!--citation 0-->
      • [IEEE TCS.II - Efficient Inference Accelerator for Binary Convolutional Neural Networks. [**`hardware`**] <!--citation 1-->
      • [IEEE TCS.I - Memory Multi-Bit Multiplication and ACcumulation in 6T SRAM Array. [**`qnn`**] <!--citation 3-->
      • [IEEE Trans. Electron Devices - -citation 0-->
      • [arXiv
      • [paper - -citation 2-->
      • [ECCV
      • [arXiv - -citation 0-->
      • [arXiv - -citation 5-->
      • [arXiv - -citation 1-->
      • [arXiv - Tensor-Cores in Turing GPUs. [**`bnn`**] [[code](https://github.com/pnnl/TCBNN)] <!--citation 1-->
      • [arXiv - level Accuracy? [**`bnn`**] [[code](https://github.com/hpi-xnor/BMXNet-v2)] [192:star:] <!--citation 13-->
      • [arXiv - -citation 3-->
      • [arXiv - -citation 0-->
      • [arXiv

    • 2019

      • [AAAI
      • [AAAI - bit CNNs via Discrete Back Propagation. [**`bnn`**]
      • [APCCAS
      • [BMVC - Net++: Improved Binary Neural Networks. [**`bnn`**]
      • [BMVC
      • [CoRR - bit DCNNs. [**`bnn`**]
      • [CoRR - Ensemble Template for Accurate Binary Convolutional Neural Networks. [**`bnn`**]
      • [CoRR
      • [CoRR
      • [CoRR
      • [CoRR - xnor/BMXNet-v2)] [193:star:]
      • [CVPR
      • [CVPR - Map Sparsity Through Low-Bit Quantization. [**`qnn`**]
      • [CVPR - Aware Automated Quantization with Mixed Precision. [**`qnn`**] [**`hardware`**] [[torch](https://github.com/mit-han-lab/haq)] [233:star:]
      • [CVPR - quantization-networks)] [82:star:]
      • [CVPR
      • [CVPR - Wise Interactions for Binary Convolutional Neural Networks. [**`bnn`**]
      • [CVPR - bit DCNNs with Circulant Back Propagation. [**`bnn`**]
      • [CVPR
      • [CVPR
      • [CVPR
      • [FPGA - Efficient Binarized Neural Network Inference on FPGA. [**`bnn`**] [**`hardware`**]
      • [ICCV - Precision and Low-Bit Neural Networks. [**`qnn`**]
      • [ICCV - bit cnns. [**`bnn`**]
      • [ICCV
      • [ICCV - Precision. [**`qnn`**]
      • [ICCV - Free Quantization Through Weight Equalization and Bias Correction. [**`qnn`**] [**`hardware`**] [[torch](https://github.com/jakc4103/DFQ)]
      • [ICCV
      • [ICML - Bit Quantization of Transformer Neural Machine Language Translation Model. [**`qnn`**] [**`nlp`**]
      • [ICLR
      • [ICLR
      • [ICIP - xnor/BMXNet-v2)] [192:star:]
      • [ICUS
      • [IJCAI - Efficient Hashing with Minimizing Quantization Loss. [**`bnn`**]
      • [IJCAI
      • [ISOCC
      • [IEEE J. Emerg. Sel. Topics Circuits Syst. - Chip Systolically Scalable Binary-Weight CNN Inference Engine. [**`hardware`**]
      • [IEEE JETC
      • [IEEE J. Solid-State Circuits - Efficient Reconfigurable Processor for Binary-and Ternary-Weight Neural Networks With Flexible Data Bit Width. [**`qnn`**]
      • [MDPI Electronics
      • [NeurIPS - differentiable Quantization. [**`qnn`**] [[torch](https://github.com/csyhhu/MetaQuant)]
      • [NeurIPS - bnn-optimization)]
      • [NeurIPS
      • [NeurIPS
      • [NeurIPS
      • [NeurIPS
      • [NeurIPS
      • [RoEduNet
      • [SiPS
      • [TMM - Modal Hashing. [**`bnn`**]
      • [TMM
      • [IEEE TCS.I - RAM: Accelerating Binary Neural Networks in High-Throughput SRAM Compute Arrays. [**`hardware`**]
      • [IEEE TCS.I - Chip Memory. [**`bnn`**]
      • [VLSI-SoC - Efficient Execution of Binary Neural Networks Using Resistive Memories. [**`bnn`**] [**`hardware`**]
      • [paper
      • [arXiv - Binarizing Networks. [**`bnn`**]
      • [arXiv
      • [arXiv - CV/dabnn)]
      • [arXiv - aware Knowledge Distillation. [**`qnn`**]
      • [arXiv

    • 2018

      • [AAAI
      • [AAAI
      • [CAAI
      • [CoRR
      • [CoRR
      • [CVPR - Step Quantization for Low-bit Neural Networks. [**`qnn`**]
      • [CVPR - bitwidth Weights and Activations. [**`qnn`**]
      • [CVPR - bitwidth Convolutional Neural Networks. [**`qnn`**]
      • [CVPR
      • [CVPR
      • [CVPR - Arithmetic-Only Inference. [**`qnn`**]
      • [ECCV - Binary Decomposition. [**`bnn`**]
      • [ECCV
      • [ECCV - Nets: Learned Quantization for Highly Accurate and Compact Deep Neural Networks. [**`qnn`**] [[tensorflow](https://github.com/microsoft/LQ-Nets)] [188:star:]
      • [ECCV - Real Net: Enhancing the Performance of 1-bit CNNs With Improved Representational Capability and Advanced Training Algorithm. [**`bnn`**] [[torch](https://github.com/liuzechun/Bi-Real-net)] [120:star:]
      • [ECCV
      • [FCCM
      • [FPL
      • [ICLR - aware Weight Quantization of Deep Networks. [**`qnn`**] [[code](https://github.com/houlu369/Loss-aware-weight-quantization)]
      • [ICLR
      • [ICLR
      • [ICLR - Precision Networks. [**`qnn`**]
      • [ICLR
      • [ICLR - Precision Network Accuracy. [**`qnn`**]
      • [IJCAI
      • [IJCAI - -citation 14-->
      • [IJCNN
      • [IPDPS
      • [NCA - based accelerators for convolutional neural networks. [**`hardware`**]
      • [NeurIPS - bit Floating Point Numbers. [**`qnn`**]
      • [NeurIPS - bit training of neural networks. [**`qnn`**] [[torch](https://github.com/eladhoffer/quantized.pytorch)]
      • [Res Math Sci
      • [TCAD - fJ/op Binary Neural Network Inference. [**`hardware`**]
      • [TRETS - R: An End-to-End Deep-Learning Framework for Fast Exploration of Quantized Neural Networks. [**`qnn`**]
      • [arXiv - xnor/BMXNet-v2)] [192:star:]
      • [CVPR - error-aware quantization for low-bit deep neural networks. [**`qnn`**]
      • [IEEE J. Solid-State Circuits - Chip Binary/Ternary Reconfigurable in-Memory Deep Neural Network Accelerator Achieving 1.4 TOPS at 0.6 W. [**`hardware`**] [**`qnn`**]
      • [TVLSI - Efficient Architecture for Binary Weight Convolutional Neural Networks. [**`bnn`**]
      • [arXiv - quantization)]

    • 2017

      • [CoRR - Source Binary Neural Network Implementation Based on MXNet. [**`bnn`**] [[code](https://github.com/hpi-xnor)]
      • [CVPR - wave Gaussian Quantization. [**`qnn`**] [[code](https://github.com/zhaoweicai/hwgq)] [118:star:]
      • [CVPR
      • [FPGA
      • [ICASSP - point optimization of deep neural networks with adaptive step size retraining. [**`qnn`**]
      • [ICCV - cnn-landmarks)] [[torch](https://github.com/1adrianb/binary-human-pose-estimation)] [207:star:]
      • [ICCV - Order Residual Quantization. [**`qnn`**]
      • [ICLR - Precision Weights. [**`qnn`**] [[torch](https://github.com/Mxbonn/INQ-pytorch)] [144:star:]
      • [ICLR - aware Binarization of Deep Networks. [**`bnn`**] [[code](https://github.com/houlu369/Loss-aware-Binarization)]
      • [ICLR - Sharing for Neural Network Compression. [__`other`__]
      • [ICLR - ternary-quantization)] [90:star:]
      • [InterSpeech
      • [IPDPSW - Chip Memory Based Binarized Convolutional Deep Neural Network Applying Batch Normalization Free Technique on an FPGA. [**`hardware`**]
      • [JETC - Outperforming FPGA Accelerator Architecture for Binary Convolutional Neural Networks. [**`hardware`**] [**`bnn`**]
      • [NeurIPS - Binary-Convolution-Network)]
      • [Neurocomputing - BNN: Binarized neural network on FPGA. [**`hardware`**]
      • [MWSCAS
      • [arXiv - Precision Architecture for Inference of Convolutional Neural Networks. [**`qnn`**] [[code](https://github.com/gudovskiy/ShiftCNN)] [53:star:]
      • [arXiv - Grained Quantization. [**`qnn`**]

    • 2016

      • [CoRR - Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients. [**`qnn`**] [[code](https://github.com/tensorpack/tensorpack/tree/master/examples/DoReFa-Net)] [5.8k:star:]
      • [ECCV - Net: ImageNet Classification Using Binary Convolutional Neural Networks. [**`bnn`**] [[torch](https://github.com/allenai/XNOR-Net)] [787:star:]
      • [ICASSP - point Performance Analysis of Recurrent Neural Networks. [**`qnn`**]
      • [NeurIPS - chris/caffe-twns)] [61:star:]
      • [NeurIPS - 1. [**`bnn`**] [[torch](https://github.com/itayhubara/BinaryNet)] [239:star:]
      • [CVPR - wu/quantized-cnn)
      • [NeurIPS - 1. [**`bnn`**] [[torch](https://github.com/itayhubara/BinaryNet)] [239:star:]

    • 2015

    • 2024

      • [arXiv - Finetuning Quantization of LLMs via Information Retention [[code](https://github.com/htqin/IR-QLoRA)]![GitHub Repo stars](https://img.shields.io/github/stars/htqin/IR-QLoRA)
      • [arXiv - Training Quantization for LLMs [[code](https://github.com/Aaronhuang-778/BiLLM)]![GitHub Repo stars](https://img.shields.io/github/stars/Aaronhuang-778/BiLLM)
      • [arXiv - Zheng/BinaryDM)]![GitHub Repo stars](https://img.shields.io/github/stars/Xingyu-Zheng/BinaryDM)
      • [arXiv - LLM: Accurate Dual-Binarization for Efficient LLMs
      • [arXiv - chip Hardware-aware Quantization
      • [arXiv
      • [arXiv - Efficient Tuning of Quantized Large Language Models
      • [arXiv - LLM: Efficiently Serving Large Language Models Through FP6-Centric Algorithm-System Co-Design
      • [arXiv
      • [arXiv - Aware Training for the Acceleration of Lightweight LLMs on the Edge [[code](https://github.com/shawnricecake/EdgeQAT)] ![GitHub Repo stars](https://img.shields.io/github/stars/shawnricecake/EdgeQAT)
      • [arXiv - Precision LLM: Low-Cost Deployment of Multiple, Different-Sized LLMs
      • [arXiv - Rank Quantization Error Reconstruction for LLMs
      • [arXiv - Free Asymmetric 2bit Quantization for KV Cache [[code](https://github.com/jy-yuan/KIVI)] ![GitHub Repo stars](https://img.shields.io/github/stars/jy-yuan/KIVI)
      • [arXiv - RelaxML/quip-sharp)] ![GitHub Repo stars](https://img.shields.io/github/stars/Cornell-RelaxML/quip-sharp)
      • [arXiv - Aware Training on Large Language Models via LoRA-wise LSQ
      • [arXiv - Aware Dequantization
      • [arXiv - Bit Quantized Large Language Model
      • [arXiv - 4-Bit LLMs via Self-Distillation [[code](https://github.com/DD-DuDa/BitDistiller)] ![GitHub Repo stars](https://img.shields.io/github/stars/DD-DuDa/BitDistiller)
      • [arXiv - bit Large Language Models
      • [DAC
      • [arXiv
      • [arXiv - ai-research/gptvq)] ![GitHub Repo stars](https://img.shields.io/github/stars/qualcomm-ai-research/gptvq)
      • [DAC - aware Post-Training Mixed-Precision Quantization for Large Language Models
      • [arXiv - Aware Mixed Precision Quantization
      • [arXiv
      • [arXiv - bound for Large Language Models with Per-tensor Quantization
      • [arXiv - PQ: Serving LLM on Heterogeneous Clusters with Phase-Aware Partition and Adaptive Quantization
      • [arXiv
      • [arXiv
      • [arXiv - free Quantization Algorithm for LLMs
      • [arXiv - KVCacheQuantization)] ![GitHub Repo stars](https://img.shields.io/github/stars/ClubieDong/QAQ-KVCacheQuantization)
      • [arXiv - Lossless Generative Inference of LLM
      • [arXiv
      • [arXiv - LLM: Truncation-aware Singular Value Decomposition for Large Language Model Compression [[code](https://github.com/AIoT-MLSys-Lab/SVD-LLM)] ![GitHub Repo stars](https://img.shields.io/github/stars/AIoT-MLSys-Lab/SVD-LLM)
      • [ICLR
      • [ICLR Practical ML for Low Resource Settings Workshop
      • [arXiv
      • [arXiv - Free 4-Bit Inference in Rotated LLMs [[code](https://github.com/spcl/QuaRot)] ![GitHub Repo stars](https://img.shields.io/github/stars/spcl/QuaRot)
      • [arXiv - compensation)] ![GitHub Repo stars](https://img.shields.io/github/stars/GongCheng1919/bias-compensation)
      • [arXiv
      • [arXiv - Training Quantization with Low-precision Minifloats and Integers on FPGAs [[code](https://github.com/Xilinx/brevitas/tree/dev/src/brevitas_examples/imagenet_classification/ptq)][__`hardware`__]
      • [arXiv - bit Quantized LLaMA3 Models? An Empirical Study [[code](https://github.com/Macaronlin/LLaMA3-Quantization)]![GitHub Repo stars](https://img.shields.io/github/stars/Macaronlin/LLaMA3-Quantization) [[HuggingFace](https://huggingface.co/LLMQ)]

  • Awesome_Efficient_LLM_Diffusion

  • Benchmark

  • Survey_Papers

  • Efficient_AIGC_Repo

Categories
Papers 880 Benchmark 3 Survey_Papers 3 Awesome_Efficient_LLM_Diffusion 2 Efficient_AIGC_Repo 1
Sub Categories
2022 342 2023 224 2020 82 2021 62 2019 60 2024 42 2018 39 2017 19 2016 7 2015 3 MQBench 2 Survey_of_Binarization 2 BiBench 1 Survey_of_Quantization 1
Keywords
pruning 1 model-quantization 1 model-compression 1 llm 1 large-language-models 1 generative-model 1 efficient-deep-learning 1 distillation 1 diffusion-models 1 awesome 1 aigc 1