{"total":274,"rows":[{"id":"2208.07339","title":"LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale","created":"2022-08-15","cited_by_count":906,"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":"2211.05102","title":"Efficiently Scaling Transformer Inference","created":"2022-11-09","cited_by_count":539,"area":null},{"id":"2306.07629","title":"SqueezeLLM: Dense-and-Sparse Quantization","created":"2023-06-13","cited_by_count":294,"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":"2212.09720","title":"The case for 4-bit precision: k-bit Inference Scaling Laws","created":"2022-12-19","cited_by_count":251,"area":null},{"id":"2209.05433","title":"FP8 Formats for Deep Learning","created":"2022-09-12","cited_by_count":196,"area":null},{"id":"2312.04564","title":"EAGLES: Efficient Accelerated 3D Gaussians with Lightweight EncodingS","created":"2023-12-07","cited_by_count":196,"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":"2109.12948","title":"Understanding and Overcoming the Challenges of Efficient Transformer Quantization","created":"2021-09-27","cited_by_count":141,"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":"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":"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":"2212.07048","title":"PD-Quant: Post-Training Quantization based on Prediction Difference Metric","created":"2022-12-14","cited_by_count":73,"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":"2310.08041","title":"QLLM: Accurate and Efficient Low-Bitwidth Quantization for Large Language Models","created":"2023-10-12","cited_by_count":64,"area":null},{"id":"2310.10049","title":"FATE-LLM: A Industrial Grade Federated Learning Framework for Large Language Models","created":"2023-10-16","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":"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":"2103.09377","title":"Multi-Prize Lottery Ticket Hypothesis: Finding Accurate Binary Neural Networks by Pruning A Randomly Weighted Network","created":"2021-03-17","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":"2103.12369","title":"ReCU: Reviving the Dead Weights in Binary Neural Networks","created":"2021-03-23","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":"2104.09987","title":"Differentiable Model Compression via Pseudo Quantization Noise","created":"2021-04-20","cited_by_count":45,"area":null},{"id":"2110.06804","title":"A comprehensive review of Binary Neural Network","created":"2021-10-11","cited_by_count":45,"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":"2111.03759","title":"MQBench: Towards Reproducible and Deployable Model Quantization Benchmark","created":"2021-11-05","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":"2108.10394","title":"Dynamic Network Quantization for Efficient Video Inference","created":"2021-08-23","cited_by_count":36,"area":null},{"id":"2312.07950","title":"CBQ: Cross-Block Quantization for Large Language Models","created":"2023-12-13","cited_by_count":34,"area":null},{"id":"2201.11113","title":"Post-training Quantization for Neural Networks with Provable Guarantees","created":"2022-01-26","cited_by_count":33,"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":"2108.13041","title":"Auto-Split: A General Framework of Collaborative Edge-Cloud AI","created":"2021-08-30","cited_by_count":30,"area":null},{"id":"2309.14592","title":"Efficient Post-training Quantization with FP8 Formats","created":"2023-09-26","cited_by_count":29,"area":"diffusion"},{"id":"2407.10960","title":"Fast Matrix Multiplications for Lookup Table-Quantized LLMs","created":"2024-07-15","cited_by_count":29,"area":null},{"id":"2102.04782","title":"Distribution Adaptive INT8 Quantization for Training CNNs","created":"2021-02-09","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":"2211.07091","title":"BiViT: Extremely Compressed Binary Vision Transformer","created":"2022-11-14","cited_by_count":28,"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":"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":"2302.06586","title":"Stitchable Neural Networks","created":"2023-02-13","cited_by_count":26,"area":null},{"id":"2109.12338","title":"Distribution-sensitive Information Retention for Accurate Binary Neural Network","created":"2021-09-25","cited_by_count":25,"area":null},{"id":"2111.12273","title":"Sharpness-aware Quantization for Deep Neural Networks","created":"2021-11-24","cited_by_count":25,"area":null},{"id":"2312.00333","title":"Green Edge AI: A Contemporary Survey","created":"2023-12-01","cited_by_count":25,"area":null},{"id":"2110.08232","title":"Fire Together Wire Together: A Dynamic Pruning Approach with Self-Supervised Mask Prediction","created":"2021-10-15","cited_by_count":24,"area":null},{"id":"2403.05894","title":"Frequency Attention for Knowledge Distillation","created":"2024-03-09","cited_by_count":24,"area":"distill"},{"id":"2210.16103","title":"Collaborative Multi-Teacher Knowledge Distillation for Learning Low Bit-width Deep Neural Networks","created":"2022-10-27","cited_by_count":23,"area":"distill"},{"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":"2307.10554","title":"EMQ: Evolving Training-free Proxies for Automated Mixed Precision Quantization","created":"2023-07-20","cited_by_count":22,"area":null},{"id":"2502.12913","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":"2106.02295","title":"Differentiable Dynamic Quantization with Mixed Precision and Adaptive Resolution","created":"2021-06-04","cited_by_count":20,"area":null},{"id":"2203.17008","title":"It's All In the Teacher: Zero-Shot Quantization Brought Closer to the Teacher","created":"2022-03-31","cited_by_count":20,"area":null},{"id":"2301.09422","title":"HALOC: Hardware-Aware Automatic Low-Rank Compression for Compact Neural Networks","created":"2023-01-20","cited_by_count":20,"area":null},{"id":"2301.09858","title":"PowerQuant: Automorphism Search for Non-Uniform Quantization","created":"2023-01-24","cited_by_count":20,"area":null},{"id":"2102.06841","title":"Collaborative Intelligence: Challenges and Opportunities","created":"2021-02-13","cited_by_count":19,"area":null},{"id":"2103.16701","title":"Charged particle tracking via edge-classifying interaction networks","created":"2021-03-30","cited_by_count":19,"area":null},{"id":"2108.06983","title":"Distance-aware Quantization","created":"2021-08-16","cited_by_count":19,"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":"2303.07129","title":"AdaptiveNet: Post-deployment Neural Architecture Adaptation for Diverse Edge Environments","created":"2023-03-13","cited_by_count":19,"area":null},{"id":"2308.06689","title":"Estimator Meets Equilibrium Perspective: A Rectified Straight Through Estimator for Binary Neural Networks Training","created":"2023-08-13","cited_by_count":19,"area":null},{"id":"2102.07981","title":"SiMaN: Sign-to-Magnitude Network Binarization","created":"2021-02-16","cited_by_count":18,"area":null},{"id":"2206.10526","title":"QuantFace: Towards Lightweight Face Recognition by Synthetic Data Low-bit Quantization","created":"2022-06-21","cited_by_count":18,"area":null},{"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":"2407.05266","title":"CLAMP-ViT: Contrastive Data-Free Learning for Adaptive Post-Training Quantization of ViTs","created":"2024-07-07","cited_by_count":17,"area":null},{"id":"2104.10640","title":"The NLP Cookbook: Modern Recipes for Transformer based Deep Learning Architectures","created":"2021-03-23","cited_by_count":16,"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":"2209.06979","title":"Efficient Quantized Sparse Matrix Operations on Tensor Cores","created":"2022-09-14","cited_by_count":16,"area":null},{"id":"2312.05431","title":"Efficient Quantization Strategies for Latent Diffusion Models","created":"2023-12-09","cited_by_count":16,"area":"diffusion"},{"id":"2307.10638","title":"Quantized Feature Distillation for Network Quantization","created":"2023-07-20","cited_by_count":15,"area":"distill"},{"id":"2104.11939","title":"Piggyback GAN: Efficient Lifelong Learning for Image Conditioned Generation","created":"2021-04-24","cited_by_count":14,"area":null},{"id":"2109.14710","title":"Convolutional Neural Network Compression through Generalized Kronecker Product Decomposition","created":"2021-09-29","cited_by_count":14,"area":null},{"id":"2211.12933","title":"Join the High Accuracy Club on ImageNet with A Binary Neural Network Ticket","created":"2022-11-23","cited_by_count":14,"area":null},{"id":"2106.12169","title":"APNN-TC: Accelerating Arbitrary Precision Neural Networks on Ampere GPU Tensor Cores","created":"2021-06-23","cited_by_count":12,"area":null},{"id":"2109.02100","title":"Cluster-Promoting Quantization with Bit-Drop for Minimizing Network Quantization Loss","created":"2021-09-05","cited_by_count":12,"area":null},{"id":"2205.08099","title":"Dimensionality Reduced Training by Pruning and Freezing Parts of a Deep Neural Network, a Survey","created":"2022-05-17","cited_by_count":12,"area":null},{"id":"2107.10624","title":"LANA: Latency Aware Network Acceleration","created":"2021-07-12","cited_by_count":11,"area":"distill"},{"id":"2112.13843","title":"BMPQ: Bit-Gradient Sensitivity Driven Mixed-Precision Quantization of DNNs from Scratch","created":"2021-12-24","cited_by_count":11,"area":null},{"id":"2309.13220","title":"Poster: Self-Supervised Quantization-Aware Knowledge Distillation","created":"2023-09-22","cited_by_count":11,"area":"distill"},{"id":"2109.01262","title":"On the Accuracy of Analog Neural Network Inference Accelerators","created":"2021-09-03","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":"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":"2205.09868","title":"Service Delay Minimization for Federated Learning over Mobile Devices","created":"2022-05-19","cited_by_count":9,"area":null},{"id":"2206.08852","title":"Channel-wise Mixed-precision Assignment for DNN Inference on Constrained Edge Nodes","created":"2022-06-17","cited_by_count":9,"area":null},{"id":"2207.10188","title":"Bitwidth-Adaptive Quantization-Aware Neural Network Training: A Meta-Learning Approach","created":"2022-07-20","cited_by_count":9,"area":null},{"id":"2212.02781","title":"QEBVerif: Quantization Error Bound Verification of Neural Networks","created":"2022-12-06","cited_by_count":9,"area":null}],"next_cursor":"100"}