{"total":782,"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":"2209.04836","title":"Git Re-Basin: Merging Models modulo Permutation Symmetries","created":"2022-09-11","cited_by_count":471,"area":null},{"id":"2110.02861","title":"8-bit Optimizers via Block-wise Quantization","created":"2021-10-06","cited_by_count":403,"area":null},{"id":"2302.03668","title":"Hard Prompts Made Easy: Gradient-Based Discrete Optimization for Prompt Tuning and Discovery","created":"2023-02-07","cited_by_count":336,"area":null},{"id":"2308.07633","title":"A Survey on Model Compression for Large Language Models","created":"2023-08-15","cited_by_count":269,"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":"2401.02436","title":"Compressed 3D Gaussian Splatting for Accelerated Novel View Synthesis","created":"2023-11-17","cited_by_count":239,"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":"2310.11453","title":"BitNet: Scaling 1-bit Transformers for Large Language Models","created":"2023-10-17","cited_by_count":189,"area":null},{"id":"2102.04010","title":"Learning N:M Fine-grained Structured Sparse Neural Networks From Scratch","created":"2021-02-08","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":"2106.08962","title":"Efficient Deep Learning: A Survey on Making Deep Learning Models Smaller, Faster, and Better","created":"2021-06-16","cited_by_count":154,"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":"2106.02852","title":"Patch Slimming for Efficient Vision Transformers","created":"2021-06-05","cited_by_count":133,"area":null},{"id":"2311.18159","title":"CompGS: Smaller and Faster Gaussian Splatting with Vector Quantization","created":"2023-11-30","cited_by_count":130,"area":null},{"id":"2303.00566","title":"Structured Pruning for Deep Convolutional Neural Networks: A survey","created":"2023-03-01","cited_by_count":122,"area":null},{"id":"2206.09557","title":"LUT-GEMM: Quantized Matrix Multiplication based on LUTs for Efficient Inference in Large-Scale Generative Language Models","created":"2022-06-20","cited_by_count":105,"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":"2104.00903","title":"Network Quantization with Element-wise Gradient Scaling","created":"2021-04-02","cited_by_count":87,"area":null},{"id":"2310.00034","title":"PB-LLM: Partially Binarized Large Language Models","created":"2023-09-29","cited_by_count":83,"area":null},{"id":"2104.08500","title":"Vision Transformer Pruning","created":"2021-04-17","cited_by_count":79,"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":"2110.13981","title":"CHIP: CHannel Independence-based Pruning for Compact Neural Networks","created":"2021-10-26","cited_by_count":78,"area":null},{"id":"2310.18313","title":"FP8-LM: Training FP8 Large Language Models","created":"2023-10-27","cited_by_count":77,"area":null},{"id":"2203.06390","title":"BiBERT: Accurate Fully Binarized BERT","created":"2022-03-12","cited_by_count":73,"area":null},{"id":"2103.08295","title":"TinyOL: TinyML with Online-Learning on Microcontrollers","created":"2021-03-15","cited_by_count":65,"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":"2402.09748","title":"Model Compression and Efficient Inference for Large Language Models: A Survey","created":"2024-02-15","cited_by_count":64,"area":null},{"id":"2103.05579","title":"hls4ml: An Open-Source Codesign Workflow to Empower Scientific Low-Power Machine Learning Devices","created":"2021-03-09","cited_by_count":62,"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":"2110.06554","title":"Towards Mixed-Precision Quantization of Neural Networks via Constrained Optimization","created":"2021-10-13","cited_by_count":61,"area":null},{"id":"2301.11913","title":"SWARM Parallelism: Training Large Models Can Be Surprisingly Communication-Efficient","created":"2023-01-27","cited_by_count":59,"area":null},{"id":"2212.09069","title":"Masked Wavelet Representation for Compact Neural Radiance Fields","created":"2022-12-18","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":"2103.12369","title":"ReCU: Reviving the Dead Weights in Binary Neural Networks","created":"2021-03-23","cited_by_count":52,"area":null},{"id":"2107.12422","title":"Towards Efficient Tensor Decomposition-Based DNN Model Compression with Optimization Framework","created":"2021-07-26","cited_by_count":52,"area":null},{"id":"2111.05193","title":"A Survey on Green Deep Learning","created":"2021-11-08","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":"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":"2502.02631","title":"ParetoQ: Improving Scaling Laws in Extremely Low-bit LLM Quantization","created":"2025-02-04","cited_by_count":46,"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":"2206.09914","title":"A Langevin-like Sampler for Discrete Distributions","created":"2022-06-20","cited_by_count":44,"area":null},{"id":"2307.16867","title":"Revisiting the Parameter Efficiency of Adapters from the Perspective of Precision Redundancy","created":"2023-07-31","cited_by_count":44,"area":null},{"id":"2103.05861","title":"Manifold Regularized Dynamic Network Pruning","created":"2021-03-10","cited_by_count":43,"area":null},{"id":"2111.09136","title":"IntraQ: Learning Synthetic Images with Intra-Class Heterogeneity for Zero-Shot Network Quantization","created":"2021-11-17","cited_by_count":43,"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":"2203.16708","title":"Task Adaptive Parameter Sharing for Multi-Task Learning","created":"2022-03-30","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":"2201.03014","title":"Glance and Focus Networks for Dynamic Visual Recognition","created":"2022-01-09","cited_by_count":41,"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":"2103.15726","title":"Slimmable Compressive Autoencoders for Practical Neural Image Compression","created":"2021-03-29","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":"2111.06061","title":"Edge-Cloud Polarization and Collaboration: A Comprehensive Survey for AI","created":"2021-11-11","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":"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":"2404.07236","title":"Lightweight Deep Learning for Resource-Constrained Environments: A Survey","created":"2024-04-08","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":"2108.10394","title":"Dynamic Network Quantization for Efficient Video Inference","created":"2021-08-23","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":"2101.10861","title":"A Review on Deep Learning in UAV Remote Sensing","created":"2021-01-22","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":"2106.02898","title":"Dynamic Resolution Network","created":"2021-06-05","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":"2408.01803","title":"STBLLM: Breaking the 1-Bit Barrier with Structured Binary LLMs","created":"2024-08-03","cited_by_count":31,"area":null},{"id":"2410.03129","title":"ARB-LLM: Alternating Refined Binarizations for Large Language Models","created":"2024-10-04","cited_by_count":31,"area":null},{"id":"2106.06091","title":"DECORE: Deep Compression with Reinforcement Learning","created":"2021-06-11","cited_by_count":29,"area":null},{"id":"2108.09187","title":"Quantization Backdoors to Deep Learning Commercial Frameworks","created":"2021-08-20","cited_by_count":29,"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":"2305.18321","title":"Training an Ising Machine with Equilibrium Propagation","created":"2023-05-22","cited_by_count":29,"area":null},{"id":"2309.01885","title":"QuantEase: Optimization-based Quantization for Language Models","created":"2023-09-05","cited_by_count":29,"area":null},{"id":"2310.02556","title":"NOLA: Compressing LoRA using Linear Combination of Random Basis","created":"2023-10-04","cited_by_count":29,"area":null},{"id":"2104.02244","title":"Content-Aware GAN Compression","created":"2021-04-06","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":"2211.07091","title":"BiViT: Extremely Compressed Binary Vision Transformer","created":"2022-11-14","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":"2201.06618","title":"VAQF: Fully Automatic Software-Hardware Co-Design Framework for Low-Bit Vision Transformer","created":"2022-01-17","cited_by_count":27,"area":null},{"id":"2406.04932","title":"Faster Than Lies: Real-time Deepfake Detection using Binary Neural Networks","created":"2024-06-07","cited_by_count":27,"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":"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":"2109.12872","title":"Meta-Aggregator: Learning to Aggregate for 1-bit Graph Neural Networks","created":"2021-09-27","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":"2208.07308","title":"Pose Forecasting in Industrial Human-Robot Collaboration","created":"2022-07-24","cited_by_count":25,"area":null},{"id":"2305.02538","title":"Cuttlefish: Low-Rank Model Training without All the Tuning","created":"2023-05-04","cited_by_count":25,"area":null},{"id":"2110.08890","title":"Network Augmentation for Tiny Deep Learning","created":"2021-10-17","cited_by_count":24,"area":null},{"id":"2210.03858","title":"AlphaTuning: Quantization-Aware Parameter-Efficient Adaptation of Large-Scale Pre-Trained Language Models","created":"2022-10-08","cited_by_count":23,"area":null}],"next_cursor":"100"}