{"total":569,"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":"2104.01136","title":"LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference","created":"2021-04-02","cited_by_count":475,"area":null},{"id":"2302.04304","title":"Q-Diffusion: Quantizing Diffusion Models","created":"2023-02-08","cited_by_count":273,"area":"diffusion"},{"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":"2209.05433","title":"FP8 Formats for Deep Learning","created":"2022-09-12","cited_by_count":196,"area":null},{"id":"2111.13824","title":"FQ-ViT: Post-Training Quantization for Fully Quantized Vision Transformer","created":"2021-11-27","cited_by_count":151,"area":null},{"id":"2306.12929","title":"Quantizable Transformers: Removing Outliers by Helping Attention Heads Do Nothing","created":"2023-06-22","cited_by_count":151,"area":null},{"id":"2402.04291","title":"BiLLM: Pushing the Limit of Post-Training Quantization for LLMs","created":"2024-02-06","cited_by_count":144,"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":"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":"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":"2210.06707","title":"Q-ViT: Accurate and Fully Quantized Low-bit Vision Transformer","created":"2022-10-13","cited_by_count":108,"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":"2110.15352","title":"MCUNetV2: Memory-Efficient Patch-based Inference for Tiny Deep Learning","created":"2021-10-28","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":"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":"2509.25149","title":"Pretraining Large Language Models with NVFP4","created":"2025-09-29","cited_by_count":76,"area":null},{"id":"2203.06390","title":"BiBERT: Accurate Fully Binarized BERT","created":"2022-03-12","cited_by_count":73,"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":"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":"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":"2106.09129","title":"A Winning Hand: Compressing Deep Networks Can Improve Out-Of-Distribution Robustness","created":"2021-06-16","cited_by_count":62,"area":null},{"id":"2103.03936","title":"Pufferfish: Communication-efficient Models At No Extra Cost","created":"2021-03-05","cited_by_count":61,"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":"2405.14852","title":"PV-Tuning: Beyond Straight-Through Estimation for Extreme LLM Compression","created":"2024-05-23","cited_by_count":61,"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":"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":"2303.09875","title":"A Dynamic Multi-Scale Voxel Flow Network for Video Prediction","created":"2023-03-17","cited_by_count":53,"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":"2112.00133","title":"PokeBNN: A Binary Pursuit of Lightweight Accuracy","created":"2021-11-30","cited_by_count":49,"area":null},{"id":"2203.10681","title":"Online Continual Learning for Embedded Devices","created":"2022-03-21","cited_by_count":49,"area":null},{"id":"2106.11309","title":"How Do Adam and Training Strategies Help BNNs Optimization?","created":"2021-06-21","cited_by_count":46,"area":null},{"id":"2212.12294","title":"FFNeRV: Flow-Guided Frame-Wise Neural Representations for Videos","created":"2022-12-23","cited_by_count":46,"area":null},{"id":"2307.02973","title":"Pruning vs Quantization: Which is Better?","created":"2023-07-06","cited_by_count":46,"area":null},{"id":"2110.06804","title":"A comprehensive review of Binary Neural Network","created":"2021-10-11","cited_by_count":45,"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":"2406.06385","title":"Low-Rank Quantization-Aware Training for LLMs","created":"2024-06-10","cited_by_count":43,"area":null},{"id":"2111.02625","title":"Qimera: Data-free Quantization with Synthetic Boundary Supporting Samples","created":"2021-11-04","cited_by_count":40,"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":"2302.01107","title":"A Survey on Efficient Training of Transformers","created":"2023-02-02","cited_by_count":39,"area":null},{"id":"2103.00841","title":"Learning Frequency Domain Approximation for Binary Neural Networks","created":"2021-03-01","cited_by_count":38,"area":null},{"id":"2208.08084","title":"AdaBin: Improving Binary Neural Networks with Adaptive Binary Sets","created":"2022-08-17","cited_by_count":38,"area":null},{"id":"2407.08296","title":"Q-GaLore: Quantized GaLore with INT4 Projection and Layer-Adaptive Low-Rank Gradients","created":"2024-07-11","cited_by_count":38,"area":null},{"id":"2411.04732","title":"Convolutional Differentiable Logic Gate Networks","created":"2024-11-07","cited_by_count":37,"area":null},{"id":"2105.11228","title":"Towards Compact CNNs via Collaborative Compression","created":"2021-05-24","cited_by_count":36,"area":null},{"id":"2108.10394","title":"Dynamic Network Quantization for Efficient Video Inference","created":"2021-08-23","cited_by_count":36,"area":null},{"id":"2104.14235","title":"Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety","created":"2021-04-29","cited_by_count":35,"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":"2201.11113","title":"Post-training Quantization for Neural Networks with Provable Guarantees","created":"2022-01-26","cited_by_count":33,"area":null},{"id":"2105.04444","title":"Continual Learning via Bit-Level Information Preserving","created":"2021-05-10","cited_by_count":32,"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":"2204.11786","title":"Enable Deep Learning on Mobile Devices: Methods, Systems, and Applications","created":"2022-04-25","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":"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":"2102.04782","title":"Distribution Adaptive INT8 Quantization for Training CNNs","created":"2021-02-09","cited_by_count":28,"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":"2211.07091","title":"BiViT: Extremely Compressed Binary Vision Transformer","created":"2022-11-14","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":"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":"2312.00678","title":"The Efficiency Spectrum of Large Language Models: An Algorithmic Survey","created":"2023-12-01","cited_by_count":26,"area":null},{"id":"2403.06213","title":"$V_kD:$ Improving Knowledge Distillation using Orthogonal Projections","created":"2024-03-10","cited_by_count":26,"area":"distill"},{"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":"2206.02915","title":"8-bit Numerical Formats for Deep Neural Networks","created":"2022-06-06","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":"2304.00253","title":"Q-DETR: An Efficient Low-Bit Quantized Detection Transformer","created":"2023-04-01","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":"2308.07209","title":"Unified Data-Free Compression: Pruning and Quantization without Fine-Tuning","created":"2023-08-14","cited_by_count":23,"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":"2102.12528","title":"Preserved central model for faster bidirectional compression in distributed settings","created":"2021-02-24","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},{"id":"2209.09004","title":"EcoFormer: Energy-Saving Attention with Linear Complexity","created":"2022-09-19","cited_by_count":21,"area":null},{"id":"2407.12327","title":"Spectra: Surprising Effectiveness of Pretraining Ternary Language Models at Scale","created":"2024-07-17","cited_by_count":21,"area":null},{"id":"2103.08870","title":"Learned Gradient Compression for Distributed Deep Learning","created":"2021-03-16","cited_by_count":20,"area":null}],"next_cursor":"100"}