{"total":261,"rows":[{"id":"2103.13630","title":"A Survey of Quantization Methods for Efficient Neural Network Inference","created":"2021-03-25","cited_by_count":815,"area":null},{"id":"2307.13304","title":"QuIP: 2-Bit Quantization of Large Language Models With Guarantees","created":"2023-07-25","cited_by_count":414,"area":null},{"id":"2201.05596","title":"DeepSpeed-MoE: Advancing Mixture-of-Experts Inference and Training to Power Next-Generation AI Scale","created":"2022-01-14","cited_by_count":404,"area":"moe"},{"id":"2306.07629","title":"SqueezeLLM: Dense-and-Sparse Quantization","created":"2023-06-13","cited_by_count":294,"area":null},{"id":"2106.14156","title":"Post-Training Quantization for Vision Transformer","created":"2021-06-27","cited_by_count":278,"area":null},{"id":"2302.04304","title":"Q-Diffusion: Quantizing Diffusion Models","created":"2023-02-08","cited_by_count":273,"area":"diffusion"},{"id":"2101.01321","title":"I-BERT: Integer-only BERT Quantization","created":"2021-01-05","cited_by_count":255,"area":null},{"id":"2203.05740","title":"QDrop: Randomly Dropping Quantization for Extremely Low-bit Post-Training Quantization","created":"2022-03-11","cited_by_count":180,"area":null},{"id":"2306.02272","title":"OWQ: Outlier-Aware Weight Quantization for Efficient Fine-Tuning and Inference of Large Language Models","created":"2023-06-04","cited_by_count":114,"area":null},{"id":"2304.07493","title":"OliVe: Accelerating Large Language Models via Hardware-friendly Outlier-Victim Pair Quantization","created":"2023-04-15","cited_by_count":92,"area":null},{"id":"2104.00903","title":"Network Quantization with Element-wise Gradient Scaling","created":"2021-04-02","cited_by_count":87,"area":null},{"id":"2205.07877","title":"A Comprehensive Survey on Model Quantization for Deep Neural Networks in Image Classification","created":"2022-05-14","cited_by_count":65,"area":null},{"id":"2405.14917","title":"SliM-LLM: Salience-Driven Mixed-Precision Quantization for Large Language Models","created":"2024-05-23","cited_by_count":63,"area":null},{"id":"2104.14129","title":"ActNN: Reducing Training Memory Footprint via 2-Bit Activation Compressed Training","created":"2021-04-29","cited_by_count":61,"area":null},{"id":"2110.06554","title":"Towards Mixed-Precision Quantization of Neural Networks via Constrained Optimization","created":"2021-10-13","cited_by_count":61,"area":null},{"id":"2211.16056","title":"NoisyQuant: Noisy Bias-Enhanced Post-Training Activation Quantization for Vision Transformers","created":"2022-11-29","cited_by_count":61,"area":null},{"id":"2306.11987","title":"Training Transformers with 4-bit Integers","created":"2023-06-21","cited_by_count":60,"area":null},{"id":"2409.17066","title":"VPTQ: Extreme Low-bit Vector Post-Training Quantization for Large Language Models","created":"2024-09-25","cited_by_count":57,"area":null},{"id":"2202.07471","title":"SQuant: On-the-Fly Data-Free Quantization via Diagonal Hessian Approximation","created":"2022-02-14","cited_by_count":55,"area":null},{"id":"2203.08368","title":"Mixed-Precision Neural Network Quantization via Learned Layer-wise Importance","created":"2022-03-16","cited_by_count":54,"area":null},{"id":"2208.14286","title":"ANT: Exploiting Adaptive Numerical Data Type for Low-bit Deep Neural Network Quantization","created":"2022-08-30","cited_by_count":51,"area":null},{"id":"2101.08940","title":"Hessian-Aware Pruning and Optimal Neural Implant","created":"2021-01-22","cited_by_count":45,"area":null},{"id":"2104.09987","title":"Differentiable Model Compression via Pseudo Quantization Noise","created":"2021-04-20","cited_by_count":45,"area":null},{"id":"2410.06270","title":"Mixture Compressor for Mixture-of-Experts LLMs Gains More","created":"2024-10-08","cited_by_count":41,"area":"moe"},{"id":"2109.07865","title":"OMPQ: Orthogonal Mixed Precision Quantization","created":"2021-09-16","cited_by_count":39,"area":null},{"id":"2404.07236","title":"Lightweight Deep Learning for Resource-Constrained Environments: A Survey","created":"2024-04-08","cited_by_count":38,"area":null},{"id":"2206.00820","title":"NIPQ: Noise proxy-based Integrated Pseudo-Quantization","created":"2022-06-02","cited_by_count":35,"area":null},{"id":"2304.10136","title":"Diversifying the High-level Features for better Adversarial Transferability","created":"2023-04-20","cited_by_count":34,"area":null},{"id":"2402.14866","title":"APTQ: Attention-aware Post-Training Mixed-Precision Quantization for Large Language Models","created":"2024-02-21","cited_by_count":34,"area":null},{"id":"2110.13041","title":"Applications and Techniques for Fast Machine Learning in Science","created":"2021-10-25","cited_by_count":32,"area":null},{"id":"2102.11289","title":"Ps and Qs: Quantization-aware pruning for efficient low latency neural network inference","created":"2021-02-22","cited_by_count":31,"area":null},{"id":"2108.12659","title":"DKM: Differentiable K-Means Clustering Layer for Neural Network Compression","created":"2021-08-28","cited_by_count":31,"area":null},{"id":"2403.12422","title":"Jetfire: Efficient and Accurate Transformer Pretraining with INT8 Data Flow and Per-Block Quantization","created":"2024-03-19","cited_by_count":31,"area":null},{"id":"2206.04459","title":"SDQ: Stochastic Differentiable Quantization with Mixed Precision","created":"2022-06-09","cited_by_count":28,"area":null},{"id":"2403.19232","title":"AZ-NAS: Assembling Zero-Cost Proxies for Network Architecture Search","created":"2024-03-28","cited_by_count":28,"area":null},{"id":"2602.03782","title":"QVLA: Not All Channels Are Equal in Vision-Language-Action Model's Quantization","created":"2026-02-03","cited_by_count":28,"area":"vla"},{"id":"2111.12273","title":"Sharpness-aware Quantization for Deep Neural Networks","created":"2021-11-24","cited_by_count":25,"area":null},{"id":"2307.10554","title":"EMQ: Evolving Training-free Proxies for Automated Mixed Precision Quantization","created":"2023-07-20","cited_by_count":22,"area":null},{"id":"2412.11549","title":"MPQ-DM: Mixed Precision Quantization for Extremely Low Bit Diffusion Models","created":"2024-12-16","cited_by_count":21,"area":"diffusion"},{"id":"2502.12913","title":"GSQ-Tuning: Group-Shared Exponents Integer in Fully Quantized Training for LLMs On-Device Fine-tuning","created":"2025-02-18","cited_by_count":21,"area":null},{"id":"2110.13541","title":"Qu-ANTI-zation: Exploiting Quantization Artifacts for Achieving Adversarial Outcomes","created":"2021-10-26","cited_by_count":19,"area":"safety"},{"id":"2405.12725","title":"Nearest is Not Dearest: Towards Practical Defense against Quantization-conditioned Backdoor Attacks","created":"2024-05-21","cited_by_count":18,"area":null},{"id":"2410.13461","title":"Progressive Mixed-Precision Decoding for Efficient LLM Inference","created":"2024-10-17","cited_by_count":18,"area":"inference"},{"id":"2302.04453","title":"Data Quality-aware Mixed-precision Quantization via Hybrid Reinforcement Learning","created":"2023-02-09","cited_by_count":17,"area":null},{"id":"2104.12766","title":"HAO: Hardware-aware neural Architecture Optimization for Efficient Inference","created":"2021-04-26","cited_by_count":16,"area":null},{"id":"2205.12268","title":"Wavelet Feature Maps Compression for Image-to-Image CNNs","created":"2022-05-24","cited_by_count":16,"area":null},{"id":"2304.06454","title":"CABM: Content-Aware Bit Mapping for Single Image Super-Resolution Network with Large Input","created":"2023-04-13","cited_by_count":16,"area":null},{"id":"2310.09499","title":"One-Shot Sensitivity-Aware Mixed Sparsity Pruning for Large Language Models","created":"2023-10-14","cited_by_count":16,"area":null},{"id":"2305.06559","title":"Patch-wise Mixed-Precision Quantization of Vision Transformer","created":"2023-05-11","cited_by_count":15,"area":null},{"id":"2112.06126","title":"Neural Network Quantization for Efficient Inference: A Survey","created":"2021-12-08","cited_by_count":14,"area":null},{"id":"2502.16638","title":"Automatic Joint Structured Pruning and Quantization for Efficient Neural Network Training and Compression","created":"2025-02-23","cited_by_count":14,"area":null},{"id":"2503.08040","title":"Accurate INT8 Training Through Dynamic Block-Level Fallback","created":"2025-03-11","cited_by_count":14,"area":null},{"id":"2509.09119","title":"Sensitivity-LoRA: Low-Load Sensitivity-Based Fine-Tuning for Large Language Models","created":"2025-09-11","cited_by_count":14,"area":null},{"id":"2102.06365","title":"Dynamic Precision Analog Computing for Neural Networks","created":"2021-02-12","cited_by_count":12,"area":null},{"id":"2301.00131","title":"Guided Hybrid Quantization for Object detection in Multimodal Remote Sensing Imagery via One-to-one Self-teaching","created":"2022-12-31","cited_by_count":12,"area":null},{"id":"2108.02720","title":"Generalizable Mixed-Precision Quantization via Attribution Rank Preservation","created":"2021-08-05","cited_by_count":11,"area":null},{"id":"2210.08502","title":"FIT: A Metric for Model Sensitivity","created":"2022-10-16","cited_by_count":11,"area":null},{"id":"2311.18129","title":"Mixed-Precision Quantization for Federated Learning on Resource-Constrained Heterogeneous Devices","created":"2023-11-29","cited_by_count":11,"area":null},{"id":"2410.13056","title":"Channel-Wise Mixed-Precision Quantization for Large Language Models","created":"2024-10-16","cited_by_count":11,"area":null},{"id":"2503.06823","title":"eMoE: Task-aware Memory Efficient Mixture-of-Experts-Based (MoE) Model Inference","created":"2025-03-10","cited_by_count":11,"area":"moe"},{"id":"2505.05530","title":"Low-bit Model Quantization for Deep Neural Networks: A Survey","created":"2025-05-08","cited_by_count":11,"area":null},{"id":"2112.11540","title":"Mixed Precision of Quantization of Transformer Language Models for Speech Recognition","created":"2021-11-29","cited_by_count":10,"area":null},{"id":"2206.07527","title":"QONNX: Representing Arbitrary-Precision Quantized Neural Networks","created":"2022-06-15","cited_by_count":10,"area":null},{"id":"2308.07650","title":"EQ-Net: Elastic Quantization Neural Networks","created":"2023-08-15","cited_by_count":10,"area":null},{"id":"2310.07147","title":"QFT: Quantized Full-parameter Tuning of LLMs with Affordable Resources","created":"2023-10-11","cited_by_count":10,"area":null},{"id":"2102.06366","title":"Confounding Tradeoffs for Neural Network Quantization","created":"2021-02-12","cited_by_count":9,"area":null},{"id":"2501.06357","title":"Mix-QViT: Mixed-Precision Vision Transformer Quantization Driven by Layer Importance and Quantization Sensitivity","created":"2025-01-10","cited_by_count":9,"area":null},{"id":"2504.14152","title":"FGMP: Fine-Grained Mixed-Precision Weight and Activation Quantization for Hardware-Accelerated LLM Inference","created":"2025-04-19","cited_by_count":9,"area":null},{"id":"2212.02770","title":"CSQ: Growing Mixed-Precision Quantization Scheme with Bi-level Continuous Sparsification","created":"2022-12-06","cited_by_count":8,"area":null},{"id":"2307.12659","title":"A Model for Every User and Budget: Label-Free and Personalized Mixed-Precision Quantization","created":"2023-07-24","cited_by_count":8,"area":null},{"id":"2308.10515","title":"QD-BEV : Quantization-aware View-guided Distillation for Multi-view 3D Object Detection","created":"2023-08-21","cited_by_count":8,"area":null},{"id":"2401.11243","title":"LRP-QViT: Mixed-Precision Vision Transformer Quantization via Layer-wise Relevance Propagation","created":"2024-01-20","cited_by_count":8,"area":null},{"id":"2509.20214","title":"Q-Palette: Fractional-Bit Quantizers Toward Optimal Bit Allocation for Efficient LLM Deployment","created":"2025-09-24","cited_by_count":8,"area":null},{"id":"2605.24011","title":"ActQuant: Sub-4-bit Action-Guided Quantization for Vision-Language-Action Models","created":"2026-05-19","cited_by_count":8,"area":"vla"},{"id":"2104.14117","title":"Hessian Aware Quantization of Spiking Neural Networks","created":"2021-04-29","cited_by_count":7,"area":null},{"id":"2203.02549","title":"Structured Pruning is All You Need for Pruning CNNs at Initialization","created":"2022-03-04","cited_by_count":7,"area":null},{"id":"2208.06064","title":"Mixed-Precision Neural Networks: A Survey","created":"2022-08-11","cited_by_count":7,"area":null},{"id":"2307.05657","title":"Mixed-Precision Quantization for Deep Vision Models with Integer Quadratic Programming","created":"2023-07-11","cited_by_count":7,"area":null},{"id":"2311.06798","title":"MetaMix: Meta-state Precision Searcher for Mixed-precision Activation Quantization","created":"2023-11-12","cited_by_count":7,"area":null},{"id":"2405.13938","title":"eXmY: A Data Type and Technique for Arbitrary Bit Precision Quantization","created":"2024-05-22","cited_by_count":7,"area":null},{"id":"2405.14569","title":"PrivCirNet: Efficient Private Inference via Block Circulant Transformation","created":"2024-05-23","cited_by_count":7,"area":null},{"id":"2412.05808","title":"SizeGS: Size-aware Compression of 3D Gaussian Splatting via Mixed Integer Programming","created":"2024-12-08","cited_by_count":7,"area":null},{"id":"2412.20185","title":"DecDEC: A Systems Approach to Advancing Low-Bit LLM Quantization","created":"2024-12-28","cited_by_count":7,"area":null},{"id":"2508.15008","title":"Neural Network Quantization for Microcontrollers: A Comprehensive Survey of Methods, Platforms, and Applications","created":"2025-08-20","cited_by_count":7,"area":null},{"id":"2605.23078","title":"GEMQ: Global Expert-Level Mixed-Precision Quantization for MoE LLMs","created":"2026-05-21","cited_by_count":7,"area":"moe"},{"id":"2606.04980","title":"AlphaQ: Calibration-Free Bit Allocation for Mixture-of-Experts Quantization","created":"2026-06-03","cited_by_count":7,"area":"moe"},{"id":"2101.04935","title":"Single-path Bit Sharing for Automatic Loss-aware Model Compression","created":"2021-01-13","cited_by_count":6,"area":null},{"id":"2103.02904","title":"Effective and Fast: A Novel Sequential Single Path Search for Mixed-Precision Quantization","created":"2021-03-04","cited_by_count":6,"area":null},{"id":"2106.07611","title":"Neuroevolution-Enhanced Multi-Objective Optimization for Mixed-Precision Quantization","created":"2021-06-14","cited_by_count":6,"area":null},{"id":"2111.00153","title":"RMSMP: A Novel Deep Neural Network Quantization Framework with Row-wise Mixed Schemes and Multiple Precisions","created":"2021-10-30","cited_by_count":6,"area":null},{"id":"2301.07247","title":"Tailor: Altering Skip Connections for Resource-Efficient Inference","created":"2023-01-18","cited_by_count":6,"area":null},{"id":"2302.06845","title":"SEAM: Searching Transferable Mixed-Precision Quantization Policy through Large Margin Regularization","created":"2023-02-14","cited_by_count":6,"area":null},{"id":"2308.03290","title":"FLIQS: One-Shot Mixed-Precision Floating-Point and Integer Quantization Search","created":"2023-08-07","cited_by_count":6,"area":null},{"id":"2309.11531","title":"EPTQ: Enhanced Post-Training Quantization via Hessian-guided Network-wise Optimization","created":"2023-09-20","cited_by_count":6,"area":null},{"id":"2309.16119","title":"ModuLoRA: Finetuning 2-Bit LLMs on Consumer GPUs by Integrating with Modular Quantizers","created":"2023-09-28","cited_by_count":6,"area":null},{"id":"2407.01054","title":"Joint Pruning and Channel-wise Mixed-Precision Quantization for Efficient Deep Neural Networks","created":"2024-07-01","cited_by_count":6,"area":null},{"id":"2503.15568","title":"Mixed precision accumulation for neural network inference guided by componentwise forward error analysis","created":"2025-03-19","cited_by_count":6,"area":null},{"id":"2102.07071","title":"Doping: A technique for efficient compression of LSTM models using sparse structured additive matrices","created":"2021-02-14","cited_by_count":5,"area":null},{"id":"2112.11438","title":"Mixed Precision Low-bit Quantization of Neural Network Language Models for Speech Recognition","created":"2021-11-29","cited_by_count":5,"area":null},{"id":"2209.06383","title":"Analysis of Quantization on MLP-based Vision Models","created":"2022-09-14","cited_by_count":5,"area":null}],"next_cursor":"100"}