{"total":815,"rows":[{"id":"2210.17323","title":"GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers","created":"2022-10-31","cited_by_count":1919,"area":null},{"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":"2301.00774","title":"SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot","created":"2023-01-02","cited_by_count":1121,"area":null},{"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":"2206.01861","title":"ZeroQuant: Efficient and Affordable Post-Training Quantization for Large-Scale Transformers","created":"2022-06-04","cited_by_count":526,"area":null},{"id":"2401.15024","title":"SliceGPT: Compress Large Language Models by Deleting Rows and Columns","created":"2024-01-26","cited_by_count":385,"area":null},{"id":"2403.03853","title":"ShortGPT: Layers in Large Language Models are More Redundant Than You Expect","created":"2024-03-06","cited_by_count":383,"area":null},{"id":"2306.03078","title":"SpQR: A Sparse-Quantized Representation for Near-Lossless LLM Weight Compression","created":"2023-06-05","cited_by_count":367,"area":null},{"id":"2208.11580","title":"Optimal Brain Compression: A Framework for Accurate Post-Training Quantization and Pruning","created":"2022-08-24","cited_by_count":322,"area":null},{"id":"2306.07629","title":"SqueezeLLM: Dense-and-Sparse Quantization","created":"2023-06-13","cited_by_count":294,"area":null},{"id":"2205.13147","title":"Matryoshka Representation Learning","created":"2022-05-26","cited_by_count":282,"area":null},{"id":"2302.04304","title":"Q-Diffusion: Quantizing Diffusion Models","created":"2023-02-08","cited_by_count":273,"area":"diffusion"},{"id":"2308.07633","title":"A Survey on Model Compression for Large Language Models","created":"2023-08-15","cited_by_count":269,"area":null},{"id":"2205.10643","title":"Self-Supervised Speech Representation Learning: A Review","created":"2022-05-21","cited_by_count":260,"area":null},{"id":"2401.06118","title":"Extreme Compression of Large Language Models via Additive Quantization","created":"2024-01-11","cited_by_count":232,"area":null},{"id":"2311.10723","title":"Large Language Models in Finance: A Survey","created":"2023-09-28","cited_by_count":226,"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":"2402.16363","title":"LLM Inference Unveiled: Survey and Roofline Model Insights","created":"2024-02-26","cited_by_count":152,"area":"inference"},{"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":"2107.00910","title":"Learned Token Pruning for Transformers","created":"2021-07-02","cited_by_count":139,"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":"2208.11625","title":"PromptFL: Let Federated Participants Cooperatively Learn Prompts Instead of Models -- Federated Learning in Age of Foundation Model","created":"2022-08-24","cited_by_count":134,"area":null},{"id":"2201.05273","title":"Pretrained Language Models for Text Generation: A Survey","created":"2022-01-14","cited_by_count":122,"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":"2207.01405","title":"I-ViT: Integer-only Quantization for Efficient Vision Transformer Inference","created":"2022-07-04","cited_by_count":95,"area":null},{"id":"2308.06077","title":"Fly-Swat or Cannon? Cost-Effective Language Model Choice via Meta-Modeling","created":"2023-08-11","cited_by_count":95,"area":null},{"id":"2403.14123","title":"AI and Memory Wall","created":"2024-03-21","cited_by_count":92,"area":null},{"id":"2312.17238","title":"Fast Inference of Mixture-of-Experts Language Models with Offloading","created":"2023-12-28","cited_by_count":91,"area":"moe"},{"id":"2208.09225","title":"FP8 Quantization: The Power of the Exponent","created":"2022-08-19","cited_by_count":88,"area":null},{"id":"2401.03205","title":"The Dawn After the Dark: An Empirical Study on Factuality Hallucination in Large Language Models","created":"2024-01-06","cited_by_count":88,"area":null},{"id":"2402.16842","title":"Asymmetry in Low-Rank Adapters of Foundation Models","created":"2024-02-26","cited_by_count":86,"area":null},{"id":"2402.15319","title":"GPTVQ: The Blessing of Dimensionality for LLM Quantization","created":"2024-02-23","cited_by_count":82,"area":null},{"id":"2302.14017","title":"Full Stack Optimization of Transformer Inference: a Survey","created":"2023-02-27","cited_by_count":80,"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":"2303.08302","title":"ZeroQuant-V2: Exploring Post-training Quantization in LLMs from Comprehensive Study to Low Rank Compensation","created":"2023-03-15","cited_by_count":79,"area":null},{"id":"2402.02244","title":"Beyond the Limits: A Survey of Techniques to Extend the Context Length in Large Language Models","created":"2024-02-03","cited_by_count":76,"area":"lr"},{"id":"2106.05022","title":"Adaptive Inference through Early-Exit Networks: Design, Challenges and Directions","created":"2021-06-09","cited_by_count":75,"area":"inference"},{"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":"2211.16386","title":"Compressing Volumetric Radiance Fields to 1 MB","created":"2022-11-29","cited_by_count":68,"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":"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":"2312.05516","title":"Stateful Large Language Model Serving with Pensieve","created":"2023-12-09","cited_by_count":61,"area":"inference"},{"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":"2504.02692","title":"GPTAQ: Efficient Finetuning-Free Quantization for Asymmetric Calibration","created":"2025-04-03","cited_by_count":60,"area":null},{"id":"2106.12379","title":"AC/DC: Alternating Compressed/DeCompressed Training of Deep Neural Networks","created":"2021-06-23","cited_by_count":59,"area":null},{"id":"2311.09755","title":"On the Impact of Calibration Data in Post-training Quantization and Pruning","created":"2023-11-16","cited_by_count":58,"area":null},{"id":"2409.00608","title":"TinyAgent: Function Calling at the Edge","created":"2024-09-01","cited_by_count":58,"area":"agents"},{"id":"2203.02250","title":"Patch Similarity Aware Data-Free Quantization for Vision Transformers","created":"2022-03-04","cited_by_count":56,"area":null},{"id":"2410.13835","title":"Active-Dormant Attention Heads: Mechanistically Demystifying Extreme-Token Phenomena in LLMs","created":"2024-10-17","cited_by_count":56,"area":null},{"id":"2402.10517","title":"Any-Precision LLM: Low-Cost Deployment of Multiple, Different-Sized LLMs","created":"2024-02-16","cited_by_count":54,"area":null},{"id":"2403.02991","title":"MADTP: Multimodal Alignment-Guided Dynamic Token Pruning for Accelerating Vision-Language Transformer","created":"2024-03-05","cited_by_count":54,"area":"inference"},{"id":"2403.12037","title":"MineDreamer: Learning to Follow Instructions via Chain-of-Imagination for Simulated-World Control","created":"2024-03-18","cited_by_count":53,"area":"wm"},{"id":"2111.05193","title":"A Survey on Green Deep Learning","created":"2021-11-08","cited_by_count":52,"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":"2111.13445","title":"How Well Do Sparse Imagenet Models Transfer?","created":"2021-11-26","cited_by_count":50,"area":null},{"id":"2302.08007","title":"With Shared Microexponents, A Little Shifting Goes a Long Way","created":"2023-02-16","cited_by_count":50,"area":null},{"id":"2302.04089","title":"ZipLM: Inference-Aware Structured Pruning of Language Models","created":"2023-02-07","cited_by_count":49,"area":null},{"id":"2305.19268","title":"Intriguing Properties of Quantization at Scale","created":"2023-05-30","cited_by_count":49,"area":null},{"id":"2402.03666","title":"QuEST: Low-bit Diffusion Model Quantization via Efficient Selective Finetuning","created":"2024-02-06","cited_by_count":49,"area":"diffusion"},{"id":"2402.16775","title":"A Comprehensive Evaluation of Quantization Strategies for Large Language Models","created":"2024-02-26","cited_by_count":48,"area":null},{"id":"2408.09632","title":"MoDeGPT: Modular Decomposition for Large Language Model Compression","created":"2024-08-19","cited_by_count":48,"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":"2412.18110","title":"SlimGPT: Layer-wise Structured Pruning for Large Language Models","created":"2024-12-24","cited_by_count":44,"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":"2309.08520","title":"Scaling Laws for Sparsely-Connected Foundation Models","created":"2023-09-15","cited_by_count":43,"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":"2310.16795","title":"QMoE: Practical Sub-1-Bit Compression of Trillion-Parameter Models","created":"2023-10-25","cited_by_count":42,"area":"moe"},{"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":"2203.08737","title":"Hardware Approximate Techniques for Deep Neural Network Accelerators: A Survey","created":"2022-03-16","cited_by_count":39,"area":null},{"id":"2210.05801","title":"Linkless Link Prediction via Relational Distillation","created":"2022-10-11","cited_by_count":39,"area":null},{"id":"2210.06640","title":"Compute-Efficient Deep Learning: Algorithmic Trends and Opportunities","created":"2022-10-13","cited_by_count":38,"area":null},{"id":"2406.04333","title":"BitsFusion: 1.99 bits Weight Quantization of Diffusion Model","created":"2024-06-06","cited_by_count":37,"area":"diffusion"},{"id":"2411.04732","title":"Convolutional Differentiable Logic Gate Networks","created":"2024-11-07","cited_by_count":37,"area":null},{"id":"2501.00365","title":"Low-Rank Adaptation for Foundation Models: A Comprehensive Review","created":"2024-12-31","cited_by_count":37,"area":null},{"id":"2201.13096","title":"SPDY: Accurate Pruning with Speedup Guarantees","created":"2022-01-31","cited_by_count":36,"area":null},{"id":"2207.11518","title":"Online Knowledge Distillation via Mutual Contrastive Learning for Visual Recognition","created":"2022-07-23","cited_by_count":36,"area":"distill"},{"id":"2411.02530","title":"A Comprehensive Study on Quantization Techniques for Large Language Models","created":"2024-10-30","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":"2201.11113","title":"Post-training Quantization for Neural Networks with Provable Guarantees","created":"2022-01-26","cited_by_count":33,"area":null},{"id":"2303.07700","title":"PATS: Patch Area Transportation with Subdivision for Local Feature Matching","created":"2023-03-14","cited_by_count":33,"area":null},{"id":"2307.12574","title":"A Good Student is Cooperative and Reliable: CNN-Transformer Collaborative Learning for Semantic Segmentation","created":"2023-07-24","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":"2209.10117","title":"A Comprehensive Survey on Trustworthy Recommender Systems","created":"2022-09-21","cited_by_count":32,"area":null},{"id":"2405.03144","title":"PTQ4SAM: Post-Training Quantization for Segment Anything","created":"2024-05-06","cited_by_count":32,"area":null},{"id":"2409.17557","title":"Joint Source-Channel Coding: Fundamentals and Recent Progress in Practical Designs","created":"2024-09-26","cited_by_count":32,"area":null},{"id":"2411.00136","title":"LLM-Inference-Bench: Inference Benchmarking of Large Language Models on AI Accelerators","created":"2024-10-31","cited_by_count":32,"area":null},{"id":"2210.12538","title":"Compressing multidimensional weather and climate data into neural networks","created":"2022-10-22","cited_by_count":31,"area":null},{"id":"2405.20915","title":"Fast yet Safe: Early-Exiting with Risk Control","created":"2024-05-31","cited_by_count":30,"area":"inference"},{"id":"2309.01885","title":"QuantEase: Optimization-based Quantization for Language Models","created":"2023-09-05","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":"2406.12930","title":"Tender: Accelerating Large Language Models via Tensor Decomposition and Runtime Requantization","created":"2024-06-16","cited_by_count":28,"area":null},{"id":"2410.13229","title":"Quamba: A Post-Training Quantization Recipe for Selective State Space Models","created":"2024-10-17","cited_by_count":28,"area":"ssm"},{"id":"2309.11932","title":"A Machine Learning-oriented Survey on Tiny Machine Learning","created":"2023-09-21","cited_by_count":27,"area":null},{"id":"2203.05025","title":"Power-of-Two Quantization for Low Bitwidth and Hardware Compliant Neural Networks","created":"2022-03-09","cited_by_count":26,"area":null},{"id":"2209.13362","title":"DELTAR: Depth Estimation from a Light-weight ToF Sensor and RGB Image","created":"2022-09-27","cited_by_count":26,"area":null}],"next_cursor":"100"}