{"list":"other","total":61,"rows":[{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"2305.14314","title":"QLoRA: Efficient Finetuning of Quantized LLMs","created":"2023-05-23","cited_by_count":3418},{"id":"1609.07843","title":"Pointer Sentinel Mixture Models","created":"2016-09-26","cited_by_count":3096},{"id":"2210.17323","title":"GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers","created":"2022-10-31","cited_by_count":1919},{"id":"1904.10509","title":"Generating Long Sequences with Sparse Transformers","created":"2019-04-23","cited_by_count":1546},{"id":"2211.10438","title":"SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models","created":"2022-11-18","cited_by_count":1386},{"id":"2301.00774","title":"SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot","created":"2023-01-02","cited_by_count":1121},{"id":"2103.13630","title":"A Survey of Quantization Methods for Efficient Neural Network Inference","created":"2021-03-25","cited_by_count":815},{"id":"2402.02750","title":"KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache","created":"2024-02-05","cited_by_count":637},{"id":"2404.00456","title":"QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs","created":"2024-03-30","cited_by_count":634},{"id":"2102.00554","title":"Sparsity in Deep Learning: Pruning and growth for efficient inference and training in neural networks","created":"2021-01-31","cited_by_count":527},{"id":"2102.05426","title":"BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstruction","created":"2021-02-10","cited_by_count":479},{"id":"2405.16406","title":"SpinQuant: LLM quantization with learned rotations","created":"2024-05-26","cited_by_count":471},{"id":"2204.07118","title":"DeiT III: Revenge of the ViT","created":"2022-04-14","cited_by_count":419},{"id":"2307.13304","title":"QuIP: 2-Bit Quantization of Large Language Models With Guarantees","created":"2023-07-25","cited_by_count":414},{"id":"2110.00476","title":"ResNet strikes back: An improved training procedure in timm","created":"2021-10-01","cited_by_count":368},{"id":"2306.03078","title":"SpQR: A Sparse-Quantized Representation for Near-Lossless LLM Weight Compression","created":"2023-06-05","cited_by_count":367},{"id":"2208.11580","title":"Optimal Brain Compression: A Framework for Accurate Post-Training Quantization and Pruning","created":"2022-08-24","cited_by_count":322},{"id":"1710.09282","title":"A Survey of Model Compression and Acceleration for Deep Neural Networks","created":"2017-10-23","cited_by_count":301},{"id":"2306.07629","title":"SqueezeLLM: Dense-and-Sparse Quantization","created":"2023-06-13","cited_by_count":294},{"id":"2101.09671","title":"Pruning and Quantization for Deep Neural Network Acceleration: A Survey","created":"2021-01-24","cited_by_count":263},{"id":"2310.08659","title":"LoftQ: LoRA-Fine-Tuning-Aware Quantization for Large Language Models","created":"2023-10-12","cited_by_count":196},{"id":"2411.05007","title":"SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models","created":"2024-11-07","cited_by_count":170},{"id":"2309.14717","title":"QA-LoRA: Quantization-Aware Low-Rank Adaptation of Large Language Models","created":"2023-09-26","cited_by_count":155},{"id":"2103.10427","title":"The Low-Rank Simplicity Bias in Deep Networks","created":"2021-03-18","cited_by_count":154},{"id":"1505.06798","title":"Accelerating Very Deep Convolutional Networks for Classification and Detection","created":"2015-05-26","cited_by_count":109},{"id":"2311.12023","title":"LQ-LoRA: Low-rank Plus Quantized Matrix Decomposition for Efficient Language Model Finetuning","created":"2023-11-20","cited_by_count":92},{"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},{"id":"2006.03669","title":"An Overview of Neural Network Compression","created":"2020-06-05","cited_by_count":59},{"id":"2405.18886","title":"Compressing Large Language Models using Low Rank and Low Precision Decomposition","created":"2024-05-29","cited_by_count":59},{"id":"2305.18403","title":"LoRAPrune: Structured Pruning Meets Low-Rank Parameter-Efficient Fine-Tuning","created":"2023-05-28","cited_by_count":53},{"id":"2307.02973","title":"Pruning vs Quantization: Which is Better?","created":"2023-07-06","cited_by_count":46},{"id":"2402.02446","title":"LQER: Low-Rank Quantization Error Reconstruction for LLMs","created":"2024-02-04","cited_by_count":41},{"id":"2512.02010","title":"Four Over Six: More Accurate NVFP4 Quantization with Adaptive Block Scaling","created":"2025-12-01","cited_by_count":35},{"id":"2201.11113","title":"Post-training Quantization for Neural Networks with Provable Guarantees","created":"2022-01-26","cited_by_count":33},{"id":"2207.06503","title":"Randomly pivoted Cholesky: Practical approximation of a kernel matrix with few entry evaluations","created":"2022-07-13","cited_by_count":32},{"id":"2509.23202","title":"Bridging the Gap Between Promise and Performance for Microscaling FP4 Quantization","created":"2025-09-27","cited_by_count":32},{"id":"2406.00800","title":"MagR: Weight Magnitude Reduction for Enhancing Post-Training Quantization","created":"2024-06-02","cited_by_count":28},{"id":"2505.11695","title":"Qronos: Correcting the Past by Shaping the Future... in Post-Training Quantization","created":"2025-05-16","cited_by_count":28},{"id":"2402.05147","title":"ApiQ: Finetuning of 2-Bit Quantized Large Language Model","created":"2024-02-07","cited_by_count":27},{"id":"2010.15979","title":"A Greedy Algorithm for Quantizing Neural Networks","created":"2020-10-29","cited_by_count":22},{"id":"2410.06040","title":"QERA: an Analytical Framework for Quantization Error Reconstruction","created":"2024-10-08","cited_by_count":22},{"id":"2409.13652","title":"OATS: Outlier-Aware Pruning Through Sparse and Low Rank Decomposition","created":"2024-09-20","cited_by_count":20},{"id":"2510.25602","title":"INT v.s. FP: A Comprehensive Study of Fine-Grained Low-bit Quantization Formats","created":"2025-10-29","cited_by_count":18},{"id":"2410.21352","title":"LLMCBench: Benchmarking Large Language Model Compression for Efficient Deployment","created":"2024-10-28","cited_by_count":16},{"id":"2508.04853","title":"Provable Post-Training Quantization: Theoretical Analysis of OPTQ and Qronos","created":"2025-08-06","cited_by_count":16},{"id":"2510.16292","title":"QSVD: Efficient Low-rank Approximation for Unified Query-Key-Value Weight Compression in Low-Precision Vision-Language Models","created":"2025-10-18","cited_by_count":16},{"id":"2109.12701","title":"Sparse Plus Low Rank Matrix Decomposition: A Discrete Optimization Approach","created":"2021-09-26","cited_by_count":14},{"id":"2502.16440","title":"Compression Scaling Laws:Unifying Sparsity and Quantization","created":"2025-02-23","cited_by_count":11},{"id":"1906.04705","title":"Fast and Accurate Least-Mean-Squares Solvers","created":"2019-06-11","cited_by_count":10},{"id":"2007.09457","title":"Compressed sensing of low-rank plus sparse matrices","created":"2020-07-18","cited_by_count":6},{"id":"2501.18475","title":"CLoQ: Enhancing Fine-Tuning of Quantized LLMs via Calibrated LoRA Initialization","created":"2025-01-30","cited_by_count":5},{"id":"2506.01863","title":"Unified Scaling Laws for Compressed Representations","created":"2025-06-02","cited_by_count":5},{"id":"2602.22268","title":"AutoQRA: Joint Optimization of Mixed-Precision Quantization and Low-rank Adapters for Efficient LLM Fine-Tuning","created":"2026-02-25","cited_by_count":5},{"id":"2604.00821","title":"Optimal Brain Decomposition for Accurate LLM Low-Rank Approximation","created":"2026-04-01","cited_by_count":4},{"id":"2502.02766","title":"Theoretical Guarantees for Low-Rank Compression of Deep Neural Networks","created":"2025-02-04","cited_by_count":3},{"id":"2508.20293","title":"Beacon: Post-Training Quantization with Integrated Grid Selection","created":"2025-08-27","cited_by_count":3},{"id":"2602.02001","title":"Preserve-Then-Quantize: Balancing Rank Budgets for Quantization Error Reconstruction in LLMs","created":"2026-02-02","cited_by_count":1}],"next_cursor":null}