{"total":94,"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":"2106.08295","title":"A White Paper on Neural Network Quantization","created":"2021-06-15","cited_by_count":472,"area":null},{"id":"2103.03123","title":"COIN: COmpression with Implicit Neural representations","created":"2021-03-03","cited_by_count":233,"area":null},{"id":"2109.12948","title":"Understanding and Overcoming the Challenges of Efficient Transformer Quantization","created":"2021-09-27","cited_by_count":141,"area":null},{"id":"2107.00910","title":"Learned Token Pruning for Transformers","created":"2021-07-02","cited_by_count":139,"area":"inference"},{"id":"2303.00566","title":"Structured Pruning for Deep Convolutional Neural Networks: A survey","created":"2023-03-01","cited_by_count":122,"area":null},{"id":"2107.07467","title":"Only Train Once: A One-Shot Neural Network Training And Pruning Framework","created":"2021-07-15","cited_by_count":70,"area":null},{"id":"2112.11312","title":"Implicit Neural Video Compression","created":"2021-12-21","cited_by_count":52,"area":null},{"id":"2307.02973","title":"Pruning vs Quantization: Which is Better?","created":"2023-07-06","cited_by_count":46,"area":null},{"id":"2209.05687","title":"PSAQ-ViT V2: Towards Accurate and General Data-Free Quantization for Vision Transformers","created":"2022-09-13","cited_by_count":42,"area":null},{"id":"2111.03759","title":"MQBench: Towards Reproducible and Deployable Model Quantization Benchmark","created":"2021-11-05","cited_by_count":40,"area":null},{"id":"2303.06862","title":"OTOV2: Automatic, Generic, User-Friendly","created":"2023-03-13","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":"2201.08442","title":"Neural Network Quantization with AI Model Efficiency Toolkit (AIMET)","created":"2022-01-20","cited_by_count":24,"area":null},{"id":"2302.05397","title":"A Practical Mixed Precision Algorithm for Post-Training Quantization","created":"2023-02-10","cited_by_count":24,"area":null},{"id":"2505.11497","title":"QVGen: Pushing the Limit of Quantized Video Generative Models","created":"2025-05-16","cited_by_count":22,"area":"diffusion"},{"id":"2203.03844","title":"Dynamic Dual Trainable Bounds for Ultra-low Precision Super-Resolution Networks","created":"2022-03-08","cited_by_count":21,"area":null},{"id":"2105.08952","title":"BatchQuant: Quantized-for-all Architecture Search with Robust Quantizer","created":"2021-05-19","cited_by_count":20,"area":null},{"id":"2103.16827","title":"Integer-only Zero-shot Quantization for Efficient Speech Recognition","created":"2021-03-31","cited_by_count":19,"area":null},{"id":"2209.06979","title":"Efficient Quantized Sparse Matrix Operations on Tensor Cores","created":"2022-09-14","cited_by_count":16,"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":"2401.01543","title":"Retraining-free Model Quantization via One-Shot Weight-Coupling Learning","created":"2024-01-03","cited_by_count":13,"area":null},{"id":"2206.10844","title":"Quantization Robust Federated Learning for Efficient Inference on Heterogeneous Devices","created":"2022-06-22","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":"2505.05530","title":"Low-bit Model Quantization for Deep Neural Networks: A Survey","created":"2025-05-08","cited_by_count":11,"area":null},{"id":"2312.15322","title":"Hardware-Aware DNN Compression via Diverse Pruning and Mixed-Precision Quantization","created":"2023-12-23","cited_by_count":10,"area":null},{"id":"2112.15139","title":"Finding the Task-Optimal Low-Bit Sub-Distribution in Deep Neural Networks","created":"2021-12-30","cited_by_count":9,"area":null},{"id":"2311.11883","title":"Efficient Neural Networks for Tiny Machine Learning: A Comprehensive Review","created":"2023-11-20","cited_by_count":9,"area":null},{"id":"2102.11062","title":"On the Effects of Quantisation on Model Uncertainty in Bayesian Neural Networks","created":"2021-02-22","cited_by_count":8,"area":null},{"id":"2203.03324","title":"Dynamic ConvNets on Tiny Devices via Nested Sparsity","created":"2022-03-07","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":"2404.01690","title":"RefQSR: Reference-based Quantization for Image Super-Resolution Networks","created":"2024-04-02","cited_by_count":8,"area":null},{"id":"2406.13046","title":"Bayesian-LoRA: LoRA based Parameter Efficient Fine-Tuning using Optimal Quantization levels and Rank Values trough Differentiable Bayesian Gates","created":"2024-06-18","cited_by_count":8,"area":null},{"id":"2110.08271","title":"Training Deep Neural Networks with Joint Quantization and Pruning of Weights and Activations","created":"2021-10-15","cited_by_count":7,"area":null},{"id":"2202.12154","title":"Towards Effective and Robust Neural Trojan Defenses via Input Filtering","created":"2022-02-24","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":"2308.05170","title":"FPGA Resource-aware Structured Pruning for Real-Time Neural Networks","created":"2023-08-09","cited_by_count":7,"area":null},{"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":"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":"2308.04595","title":"Quantization Aware Factorization for Deep Neural Network Compression","created":"2023-08-08","cited_by_count":6,"area":null},{"id":"2312.09411","title":"OTOv3: Automatic Architecture-Agnostic Neural Network Training and Compression from Structured Pruning to Erasing Operators","created":"2023-12-15","cited_by_count":6,"area":null},{"id":"2312.10588","title":"Post-Training Quantization for Re-parameterization via Coarse & Fine Weight Splitting","created":"2023-12-17","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":"2409.17092","title":"Accumulator-Aware Post-Training Quantization for Large Language Models","created":"2024-09-25","cited_by_count":6,"area":null},{"id":"2103.01435","title":"Improved Techniques for Quantizing Deep Networks with Adaptive Bit-Widths","created":"2021-03-02","cited_by_count":5,"area":null},{"id":"2409.14330","title":"Thinking in Granularity: Dynamic Quantization for Image Super-Resolution by Intriguing Multi-Granularity Clues","created":"2024-09-22","cited_by_count":5,"area":null},{"id":"2501.18665","title":"BARNN: A Bayesian Autoregressive and Recurrent Neural Network","created":"2025-01-30","cited_by_count":5,"area":null},{"id":"2503.17513","title":"Improving Quantization with Post-Training Model Expansion","created":"2025-03-21","cited_by_count":5,"area":null},{"id":"2507.07877","title":"Edge-ASR: Towards Low-Bit Quantization of Automatic Speech Recognition Models","created":"2025-07-10","cited_by_count":5,"area":null},{"id":"2206.08869","title":"Fast Lossless Neural Compression with Integer-Only Discrete Flows","created":"2022-06-17","cited_by_count":4,"area":null},{"id":"2302.07612","title":"Towards Optimal Compression: Joint Pruning and Quantization","created":"2023-02-15","cited_by_count":4,"area":null},{"id":"2307.04535","title":"QBitOpt: Fast and Accurate Bitwidth Reallocation during Training","created":"2023-07-10","cited_by_count":4,"area":null},{"id":"2407.00761","title":"Improving the performance of Stein variational inference through extreme sparsification of physically-constrained neural network models","created":"2024-06-30","cited_by_count":4,"area":null},{"id":"2409.09085","title":"HESSO: Towards Automatic Efficient and User Friendly Any Neural Network Training and Pruning","created":"2024-09-11","cited_by_count":4,"area":null},{"id":"2103.10051","title":"Data-free mixed-precision quantization using novel sensitivity metric","created":"2021-03-18","cited_by_count":3,"area":null},{"id":"2203.11323","title":"Training Quantised Neural Networks with STE Variants: the Additive Noise Annealing Algorithm","created":"2022-03-21","cited_by_count":3,"area":null},{"id":"2207.11048","title":"Quantized Sparse Weight Decomposition for Neural Network Compression","created":"2022-07-22","cited_by_count":3,"area":null},{"id":"2304.08400","title":"ATHEENA: A Toolflow for Hardware Early-Exit Network Automation","created":"2023-04-17","cited_by_count":3,"area":null},{"id":"2307.02894","title":"Free Bits: Latency Optimization of Mixed-Precision Quantized Neural Networks on the Edge","created":"2023-07-06","cited_by_count":3,"area":null},{"id":"2411.01417","title":"BF-IMNA: A Bit Fluid In-Memory Neural Architecture for Neural Network Acceleration","created":"2024-11-03","cited_by_count":3,"area":null},{"id":"2505.09361","title":"Efficient Mixed Precision Quantization in Graph Neural Networks","created":"2025-05-14","cited_by_count":3,"area":null},{"id":"2606.04115","title":"dMX: Differentiable Mixed-Precision Assignment for Low-Precision Floating-Point Formats","created":"2026-06-02","cited_by_count":3,"area":null},{"id":"2302.10483","title":"Structured Bayesian Compression for Deep Neural Networks Based on The Turbo-VBI Approach","created":"2023-02-21","cited_by_count":2,"area":null},{"id":"2305.05888","title":"Distribution-Flexible Subset Quantization for Post-Quantizing Super-Resolution Networks","created":"2023-05-10","cited_by_count":2,"area":null},{"id":"2308.09511","title":"ResQ: Residual Quantization for Video Perception","created":"2023-08-18","cited_by_count":2,"area":null},{"id":"2309.14157","title":"LAPP: Layer Adaptive Progressive Pruning for Compressing CNNs from Scratch","created":"2023-09-25","cited_by_count":2,"area":null},{"id":"2402.17706","title":"Adaptive quantization with mixed-precision based on low-cost proxy","created":"2024-02-27","cited_by_count":2,"area":null},{"id":"2505.17856","title":"Stochastic Weight Sharing for Bayesian Neural Networks","created":"2025-05-23","cited_by_count":2,"area":null},{"id":"2507.10340","title":"Text Embedding Knows How to Quantize Text-Guided Diffusion Models","created":"2025-07-14","cited_by_count":2,"area":"diffusion"},{"id":"2508.09500","title":"MiCo: End-to-End Mixed Precision Neural Network Co-Exploration Framework for Edge AI","created":"2025-08-13","cited_by_count":2,"area":null},{"id":"2511.18689","title":"QuantKAN: A Unified Quantization Framework for Kolmogorov Arnold Networks","created":"2025-11-24","cited_by_count":2,"area":null},{"id":"2512.12981","title":"CoDeQ: End-to-End Joint Model Compression with Dead-Zone Quantizer for High-Sparsity and Low-Precision Networks","created":"2025-12-15","cited_by_count":2,"area":null},{"id":"2206.12191","title":"Computational Complexity Evaluation of Neural Network Applications in Signal Processing","created":"2022-06-24","cited_by_count":1,"area":null},{"id":"2302.14458","title":"Ultra-low Precision Multiplication-free Training for Deep Neural Networks","created":"2023-02-28","cited_by_count":1,"area":null},{"id":"2306.05785","title":"End-to-End Neural Network Compression via $\\frac{\\ell_1}{\\ell_2}$ Regularized Latency Surrogates","created":"2023-06-09","cited_by_count":1,"area":null},{"id":"2403.20080","title":"Mixed-precision Supernet Training from Vision Foundation Models using Low Rank Adapter","created":"2024-03-29","cited_by_count":1,"area":null},{"id":"2404.07532","title":"Bayesian Federated Model Compression for Communication and Computation Efficiency","created":"2024-04-11","cited_by_count":1,"area":null},{"id":"2404.09737","title":"Quantization of Large Language Models with an Overdetermined Basis","created":"2024-04-15","cited_by_count":1,"area":null},{"id":"2409.20138","title":"Constraint Guided Model Quantization of Neural Networks","created":"2024-09-30","cited_by_count":1,"area":null},{"id":"2411.00907","title":"On the Impact of White-box Deployment Strategies for Edge AI on Latency and Model Performance","created":"2024-11-01","cited_by_count":1,"area":null},{"id":"2505.08793","title":"Onboard Optimization and Learning: A Survey","created":"2025-05-07","cited_by_count":1,"area":null},{"id":"2110.12844","title":"Reconstructing Pruned Filters using Cheap Spatial Transformations","created":"2021-10-25","cited_by_count":0,"area":null},{"id":"2303.17061","title":"A Tensor-based Convolutional Neural Network for Small Dataset Classification","created":"2023-03-29","cited_by_count":0,"area":null},{"id":"2306.08960","title":"Neural Network Compression using Binarization and Few Full-Precision Weights","created":"2023-06-15","cited_by_count":0,"area":null},{"id":"2311.02772","title":"Attention or Convolution: Transformer Encoders in Audio Language Models for Inference Efficiency","created":"2023-11-05","cited_by_count":0,"area":null},{"id":"2408.08681","title":"A Mean Field Ansatz for Zero-Shot Weight Transfer","created":"2024-08-16","cited_by_count":0,"area":null},{"id":"2506.22871","title":"P$^2$U: Progressive Precision Update For Efficient Model Distribution","created":"2025-06-28","cited_by_count":0,"area":null},{"id":"2510.08999","title":"SQS: Bayesian DNN Compression through Sparse Quantized Sub-distributions","created":"2025-10-10","cited_by_count":0,"area":null},{"id":"2605.02086","title":"GETA-3DGS: Automatic Joint Structured Pruning and Quantization for 3D Gaussian Splatting","created":"2026-05-03","cited_by_count":0,"area":null},{"id":"2607.24981","title":"Enabling Fully Integer-Only Inference for Lightweight Detection Transformers","created":"2026-07-27","cited_by_count":0,"area":null},{"id":"2608.00859","title":"SparseKAN: Compressing Kolmogorov--Arnold Networks Across Basis Functions, Neurons, and Bits","created":"2026-08-01","cited_by_count":0,"area":null},{"id":"2608.05499","title":"APQF: Agentic Profiling-Guided Structured Pruning and Mixed-Precision Quantization with Adaptive Fine-Tuning","created":"2026-08-06","cited_by_count":0,"area":"agents"},{"id":"2608.06916","title":"MiCoPro: End-to-End Mixed Precision HW/SW Co-design with HW-aware Proxy Model","created":"2026-08-07","cited_by_count":0,"area":null},{"id":"2610.06026","title":"Differentiable Bit-Widths: Co-optimizing Pruning and Quantization via SVD for Ultra-Efficient LLM Compression","created":"2026-10-05","cited_by_count":0,"area":null}],"next_cursor":null}