{"total":467,"rows":[{"id":"2306.00978","title":"AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration","created":"2023-06-01","cited_by_count":1298,"area":null},{"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":"2102.05426","title":"BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstruction","created":"2021-02-10","cited_by_count":479,"area":null},{"id":"2308.13137","title":"OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models","created":"2023-08-25","cited_by_count":424,"area":null},{"id":"2305.17888","title":"LLM-QAT: Data-Free Quantization Aware Training for Large Language Models","created":"2023-05-29","cited_by_count":324,"area":null},{"id":"2106.14156","title":"Post-Training Quantization for Vision Transformer","created":"2021-06-27","cited_by_count":278,"area":null},{"id":"2101.09671","title":"Pruning and Quantization for Deep Neural Network Acceleration: A Survey","created":"2021-01-24","cited_by_count":263,"area":null},{"id":"2101.01321","title":"I-BERT: Integer-only BERT Quantization","created":"2021-01-05","cited_by_count":255,"area":null},{"id":"2209.13325","title":"Outlier Suppression: Pushing the Limit of Low-bit Transformer Language Models","created":"2022-09-27","cited_by_count":181,"area":null},{"id":"2111.12293","title":"PTQ4ViT: Post-training quantization for vision transformers with twin uniform quantization","created":"2021-11-24","cited_by_count":179,"area":null},{"id":"2206.15472","title":"On-Device Training Under 256KB Memory","created":"2022-06-30","cited_by_count":160,"area":null},{"id":"2402.16363","title":"LLM Inference Unveiled: Survey and Roofline Model Insights","created":"2024-02-26","cited_by_count":152,"area":"inference"},{"id":"2212.08254","title":"RepQ-ViT: Scale Reparameterization for Post-Training Quantization of Vision Transformers","created":"2022-12-16","cited_by_count":137,"area":null},{"id":"2203.11086","title":"Overcoming Oscillations in Quantization-Aware Training","created":"2022-03-21","cited_by_count":119,"area":null},{"id":"2304.01089","title":"RPTQ: Reorder-based Post-training Quantization for Large Language Models","created":"2023-04-03","cited_by_count":116,"area":null},{"id":"2207.01405","title":"I-ViT: Integer-only Quantization for Efficient Vision Transformer Inference","created":"2022-07-04","cited_by_count":95,"area":null},{"id":"2406.17343","title":"Q-DiT: Accurate Post-Training Quantization for Diffusion Transformers","created":"2024-06-25","cited_by_count":94,"area":"diffusion"},{"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":"2110.15352","title":"MCUNetV2: Memory-Efficient Patch-based Inference for Tiny Deep Learning","created":"2021-10-28","cited_by_count":89,"area":null},{"id":"2205.00459","title":"Training High-Performance Low-Latency Spiking Neural Networks by Differentiation on Spike Representation","created":"2022-05-01","cited_by_count":89,"area":null},{"id":"2208.09225","title":"FP8 Quantization: The Power of the Exponent","created":"2022-08-19","cited_by_count":88,"area":null},{"id":"2104.00903","title":"Network Quantization with Element-wise Gradient Scaling","created":"2021-04-02","cited_by_count":87,"area":null},{"id":"2408.11850","title":"PEARL: Parallel Speculative Decoding with Adaptive Draft Length","created":"2024-08-13","cited_by_count":85,"area":"inference"},{"id":"2105.03620","title":"ABCNet v2: Adaptive Bezier-Curve Network for Real-time End-to-end Text Spotting","created":"2021-05-08","cited_by_count":84,"area":null},{"id":"2306.02316","title":"Temporal Dynamic Quantization for Diffusion Models","created":"2023-06-04","cited_by_count":81,"area":"diffusion"},{"id":"2111.14826","title":"Nonuniform-to-Uniform Quantization: Towards Accurate Quantization via Generalized Straight-Through Estimation","created":"2021-11-29","cited_by_count":79,"area":null},{"id":"2203.10705","title":"Compression of Generative Pre-trained Language Models via Quantization","created":"2022-03-21","cited_by_count":79,"area":null},{"id":"2212.07048","title":"PD-Quant: Post-Training Quantization based on Prediction Difference Metric","created":"2022-12-14","cited_by_count":73,"area":null},{"id":"2210.08277","title":"Deep Differentiable Logic Gate Networks","created":"2022-10-15","cited_by_count":67,"area":null},{"id":"2403.12544","title":"AffineQuant: Affine Transformation Quantization for Large Language Models","created":"2024-03-19","cited_by_count":67,"area":null},{"id":"2201.00814","title":"Vision Transformer Slimming: Multi-Dimension Searching in Continuous Optimization Space","created":"2022-01-03","cited_by_count":66,"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":"2102.04503","title":"VS-Quant: Per-vector Scaled Quantization for Accurate Low-Precision Neural Network Inference","created":"2021-02-08","cited_by_count":64,"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":"2304.09145","title":"Outlier Suppression+: Accurate quantization of large language models by equivalent and optimal shifting and scaling","created":"2023-04-18","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":"2302.02210","title":"Oscillation-free Quantization for Low-bit Vision Transformers","created":"2023-02-04","cited_by_count":57,"area":null},{"id":"2203.02250","title":"Patch Similarity Aware Data-Free Quantization for Vision Transformers","created":"2022-03-04","cited_by_count":56,"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":"2112.11312","title":"Implicit Neural Video Compression","created":"2021-12-21","cited_by_count":52,"area":null},{"id":"2205.13016","title":"BiT: Robustly Binarized Multi-distilled Transformer","created":"2022-05-25","cited_by_count":52,"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":"2112.00133","title":"PokeBNN: A Binary Pursuit of Lightweight Accuracy","created":"2021-11-30","cited_by_count":49,"area":null},{"id":"2305.18723","title":"Towards Accurate Post-training Quantization for Diffusion Models","created":"2023-05-30","cited_by_count":47,"area":"diffusion"},{"id":"2410.08119","title":"Q-VLM: Post-training Quantization for Large Vision-Language Models","created":"2024-10-10","cited_by_count":47,"area":"mllm"},{"id":"2307.02973","title":"Pruning vs Quantization: Which is Better?","created":"2023-07-06","cited_by_count":46,"area":null},{"id":"2211.02048","title":"Efficient Spatially Sparse Inference for Conditional GANs and Diffusion Models","created":"2022-11-03","cited_by_count":45,"area":"diffusion"},{"id":"2103.15263","title":"Zero-shot Adversarial Quantization","created":"2021-03-29","cited_by_count":44,"area":null},{"id":"2302.08469","title":"Hardware-aware training for large-scale and diverse deep learning inference workloads using in-memory computing-based accelerators","created":"2023-02-16","cited_by_count":43,"area":null},{"id":"2103.07156","title":"Learnable Companding Quantization for Accurate Low-bit Neural Networks","created":"2021-03-12","cited_by_count":42,"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":"2504.09629","title":"Quantization Error Propagation: Revisiting Layer-Wise Post-Training Quantization","created":"2025-04-13","cited_by_count":41,"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":"2403.19076","title":"Tiny Machine Learning: Progress and Futures","created":"2024-03-28","cited_by_count":40,"area":null},{"id":"2102.10462","title":"BSQ: Exploring Bit-Level Sparsity for Mixed-Precision Neural Network Quantization","created":"2021-02-20","cited_by_count":39,"area":null},{"id":"2109.07865","title":"OMPQ: Orthogonal Mixed Precision Quantization","created":"2021-09-16","cited_by_count":39,"area":null},{"id":"2203.08737","title":"Hardware Approximate Techniques for Deep Neural Network Accelerators: A Survey","created":"2022-03-16","cited_by_count":39,"area":null},{"id":"2310.09259","title":"QUIK: Towards End-to-End 4-Bit Inference on Generative Large Language Models","created":"2023-10-13","cited_by_count":39,"area":null},{"id":"2505.14669","title":"Quartet: Native FP4 Training Can Be Optimal for Large Language Models","created":"2025-05-20","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":"2103.03467","title":"Teachers Do More Than Teach: Compressing Image-to-Image Models","created":"2021-03-05","cited_by_count":37,"area":null},{"id":"2110.10486","title":"A TinyML Platform for On-Device Continual Learning with Quantized Latent Replays","created":"2021-10-20","cited_by_count":37,"area":null},{"id":"2201.07703","title":"Q-ViT: Fully Differentiable Quantization for Vision Transformer","created":"2022-01-19","cited_by_count":37,"area":null},{"id":"2411.04732","title":"Convolutional Differentiable Logic Gate Networks","created":"2024-11-07","cited_by_count":37,"area":null},{"id":"2108.10394","title":"Dynamic Network Quantization for Efficient Video Inference","created":"2021-08-23","cited_by_count":36,"area":null},{"id":"2412.14363","title":"ResQ: Mixed-Precision Quantization of Large Language Models with Low-Rank Residuals","created":"2024-12-18","cited_by_count":36,"area":null},{"id":"2206.00820","title":"NIPQ: Noise proxy-based Integrated Pseudo-Quantization","created":"2022-06-02","cited_by_count":35,"area":null},{"id":"2307.07982","title":"A Survey of Techniques for Optimizing Transformer Inference","created":"2023-07-16","cited_by_count":35,"area":null},{"id":"2205.11098","title":"PointDistiller: Structured Knowledge Distillation Towards Efficient and Compact 3D Detection","created":"2022-05-23","cited_by_count":33,"area":"distill"},{"id":"2312.13789","title":"TinySAM: Pushing the Envelope for Efficient Segment Anything Model","created":"2023-12-21","cited_by_count":33,"area":"distill"},{"id":"2110.13041","title":"Applications and Techniques for Fast Machine Learning in Science","created":"2021-10-25","cited_by_count":32,"area":null},{"id":"2105.10288","title":"Extremely Lightweight Quantization Robust Real-Time Single-Image Super Resolution for Mobile Devices","created":"2021-05-21","cited_by_count":30,"area":null},{"id":"2108.13041","title":"Auto-Split: A General Framework of Collaborative Edge-Cloud AI","created":"2021-08-30","cited_by_count":30,"area":null},{"id":"2208.05163","title":"Auto-ViT-Acc: An FPGA-Aware Automatic Acceleration Framework for Vision Transformer with Mixed-Scheme Quantization","created":"2022-08-10","cited_by_count":29,"area":null},{"id":"2209.02681","title":"How important are activation functions in regression and classification? A survey, performance comparison, and future directions","created":"2022-09-06","cited_by_count":29,"area":null},{"id":"2309.14592","title":"Efficient Post-training Quantization with FP8 Formats","created":"2023-09-26","cited_by_count":29,"area":"diffusion"},{"id":"2407.12951","title":"AdaLog: Post-Training Quantization for Vision Transformers with Adaptive Logarithm Quantizer","created":"2024-07-17","cited_by_count":29,"area":null},{"id":"2202.05239","title":"F8Net: Fixed-Point 8-bit Only Multiplication for Network Quantization","created":"2022-02-10","cited_by_count":28,"area":null},{"id":"2206.04459","title":"SDQ: Stochastic Differentiable Quantization with Mixed Precision","created":"2022-06-09","cited_by_count":28,"area":null},{"id":"2406.00800","title":"MagR: Weight Magnitude Reduction for Enhancing Post-Training Quantization","created":"2024-06-02","cited_by_count":28,"area":null},{"id":"2207.10345","title":"CADyQ: Content-Aware Dynamic Quantization for Image Super-Resolution","created":"2022-07-21","cited_by_count":27,"area":null},{"id":"2402.05147","title":"ApiQ: Finetuning of 2-Bit Quantized Large Language Model","created":"2024-02-07","cited_by_count":27,"area":null},{"id":"2105.03536","title":"Pareto-Optimal Quantized ResNet Is Mostly 4-bit","created":"2021-05-07","cited_by_count":26,"area":null},{"id":"2112.10769","title":"Accurate Neural Training with 4-bit Matrix Multiplications at Standard Formats","created":"2021-12-19","cited_by_count":26,"area":null},{"id":"2206.06501","title":"Optimal Clipping and Magnitude-aware Differentiation for Improved Quantization-aware Training","created":"2022-06-13","cited_by_count":26,"area":null},{"id":"2308.15949","title":"Latency-aware Unified Dynamic Networks for Efficient Image Recognition","created":"2023-08-30","cited_by_count":26,"area":null},{"id":"2111.12273","title":"Sharpness-aware Quantization for Deep Neural Networks","created":"2021-11-24","cited_by_count":25,"area":null},{"id":"2412.01034","title":"Quantization-Aware Imitation-Learning for Resource-Efficient Robotic Control","created":"2024-12-02","cited_by_count":25,"area":"vla"},{"id":"2105.11683","title":"Towards Compact Single Image Super-Resolution via Contrastive Self-distillation","created":"2021-05-25","cited_by_count":24,"area":"distill"},{"id":"2203.15952","title":"4-bit Conformer with Native Quantization Aware Training for Speech Recognition","created":"2022-03-29","cited_by_count":24,"area":null},{"id":"2404.03605","title":"Mitigating the Impact of Outlier Channels for Language Model Quantization with Activation Regularization","created":"2024-04-04","cited_by_count":23,"area":null},{"id":"2103.17267","title":"Bit-Mixer: Mixed-precision networks with runtime bit-width selection","created":"2021-03-31","cited_by_count":22,"area":null},{"id":"2301.11233","title":"BiBench: Benchmarking and Analyzing Network Binarization","created":"2023-01-26","cited_by_count":22,"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":"2502.05003","title":"QuEST: Stable Training of LLMs with 1-Bit Weights and Activations","created":"2025-02-07","cited_by_count":22,"area":null},{"id":"2601.20088","title":"Quantization-Aware Distillation for NVFP4 Inference Accuracy Recovery","created":"2026-01-27","cited_by_count":22,"area":"mllm"},{"id":"2103.15760","title":"Shrinking Bigfoot: Reducing wav2vec 2.0 footprint","created":"2021-03-29","cited_by_count":21,"area":null},{"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}],"next_cursor":"100"}