{"list":"other","total":60,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"id":"1803.05457","title":"Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge","created":"2018-03-14","cited_by_count":4886},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"1905.07830","title":"HellaSwag: Can a Machine Really Finish Your Sentence?","created":"2019-05-19","cited_by_count":4100},{"id":"2310.06825","title":"Mistral 7B","created":"2023-10-10","cited_by_count":3164},{"id":"1609.07843","title":"Pointer Sentinel Mixture Models","created":"2016-09-26","cited_by_count":3096},{"id":"1911.11641","title":"PIQA: Reasoning about Physical Commonsense in Natural Language","created":"2019-11-26","cited_by_count":2883},{"id":"1506.02626","title":"Learning both Weights and Connections for Efficient Neural Networks","created":"2015-06-08","cited_by_count":2031},{"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":"1708.00055","title":"SemEval-2017 Task 1: Semantic Textual Similarity - Multilingual and Cross-lingual Focused Evaluation","created":"2017-07-31","cited_by_count":1001},{"id":"1606.06031","title":"The LAMBADA dataset: Word prediction requiring a broad discourse context","created":"2016-06-20","cited_by_count":992},{"id":"2103.13630","title":"A Survey of Quantization Methods for Efficient Neural Network Inference","created":"2021-03-25","cited_by_count":815},{"id":"2306.11695","title":"A Simple and Effective Pruning Approach for Large Language Models","created":"2023-06-20","cited_by_count":800},{"id":"2404.00456","title":"QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs","created":"2024-03-30","cited_by_count":634},{"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":"2401.15024","title":"SliceGPT: Compress Large Language Models by Deleting Rows and Columns","created":"2024-01-26","cited_by_count":385},{"id":"2402.04396","title":"QuIP#: Even Better LLM Quantization with Hadamard Incoherence and Lattice Codebooks","created":"2024-02-06","cited_by_count":378},{"id":"1502.02551","title":"Deep Learning with Limited Numerical Precision","created":"2015-02-09","cited_by_count":376},{"id":"2308.07633","title":"A Survey on Model Compression for Large Language Models","created":"2023-08-15","cited_by_count":269},{"id":"2101.09671","title":"Pruning and Quantization for Deep Neural Network Acceleration: A Survey","created":"2021-01-24","cited_by_count":263},{"id":"1911.03852","title":"HAWQ-V2: Hessian Aware trace-Weighted Quantization of Neural Networks","created":"2019-11-10","cited_by_count":261},{"id":"2310.17157","title":"Deja Vu: Contextual Sparsity for Efficient LLMs at Inference Time","created":"2023-10-26","cited_by_count":252},{"id":"2403.07378","title":"SVD-LLM: Truncation-aware Singular Value Decomposition for Large Language Model Compression","created":"2024-03-12","cited_by_count":243},{"id":"2406.01721","title":"DuQuant: Distributing Outliers via Dual Transformation Makes Stronger Quantized LLMs","created":"2024-06-03","cited_by_count":167},{"id":"2212.08254","title":"RepQ-ViT: Scale Reparameterization for Post-Training Quantization of Vision Transformers","created":"2022-12-16","cited_by_count":137},{"id":"2203.07259","title":"The Optimal BERT Surgeon: Scalable and Accurate Second-Order Pruning for Large Language Models","created":"2022-03-14","cited_by_count":115},{"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},{"id":"2006.08509","title":"APQ: Joint Search for Network Architecture, Pruning and Quantization Policy","created":"2020-06-15","cited_by_count":99},{"id":"2402.09025","title":"SLEB: Streamlining LLMs through Redundancy Verification and Elimination of Transformer Blocks","created":"2024-02-14","cited_by_count":97},{"id":"2111.14826","title":"Nonuniform-to-Uniform Quantization: Towards Accurate Quantization via Generalized Straight-Through Estimation","created":"2021-11-29","cited_by_count":79},{"id":"2106.00085","title":"Language Model Evaluation Beyond Perplexity","created":"2021-05-31","cited_by_count":78},{"id":"2410.23771","title":"What is Wrong with Perplexity for Long-context Language Modeling?","created":"2024-10-31","cited_by_count":69},{"id":"2202.07105","title":"A Survey on Model Compression and Acceleration for Pretrained Language Models","created":"2022-02-15","cited_by_count":45},{"id":"2307.07982","title":"A Survey of Techniques for Optimizing Transformer Inference","created":"2023-07-16","cited_by_count":35},{"id":"2410.03765","title":"Basis Sharing: Cross-Layer Parameter Sharing for Large Language Model Compression","created":"2024-10-02","cited_by_count":35},{"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},{"id":"2303.04185","title":"Gradient-Free Structured Pruning with Unlabeled Data","created":"2023-03-07","cited_by_count":26},{"id":"2301.12017","title":"Understanding INT4 Quantization for Transformer Models: Latency Speedup, Composability, and Failure Cases","created":"2023-01-27","cited_by_count":23},{"id":"2106.14681","title":"PQK: Model Compression via Pruning, Quantization, and Knowledge Distillation","created":"2021-06-25","cited_by_count":21},{"id":"2305.10727","title":"Boost Vision Transformer with GPU-Friendly Sparsity and Quantization","created":"2023-05-18","cited_by_count":20},{"id":"2205.11141","title":"OPQ: Compressing Deep Neural Networks with One-shot Pruning-Quantization","created":"2022-05-23","cited_by_count":19},{"id":"2405.20935","title":"Effective Interplay between Sparsity and Quantization: From Theory to Practice","created":"2024-05-31","cited_by_count":19},{"id":"2407.02068","title":"LPViT: Low-Power Semi-structured Pruning for Vision Transformers","created":"2024-07-02","cited_by_count":16},{"id":"2502.16638","title":"Automatic Joint Structured Pruning and Quantization for Efficient Neural Network Training and Compression","created":"2025-02-23","cited_by_count":14},{"id":"2308.03449","title":"Accurate Retraining-free Pruning for Pretrained Encoder-based Language Models","created":"2023-08-07","cited_by_count":11},{"id":"2202.07861","title":"Practical Network Acceleration with Tiny Sets","created":"2022-02-16","cited_by_count":10},{"id":"2505.09188","title":"Zero-shot Quantization: A Comprehensive Survey","created":"2025-05-14","cited_by_count":8},{"id":"2407.01054","title":"Joint Pruning and Channel-wise Mixed-Precision Quantization for Efficient Deep Neural Networks","created":"2024-07-01","cited_by_count":6},{"id":"2310.11611","title":"In defense of parameter sharing for model-compression","created":"2023-10-17","cited_by_count":5},{"id":"2506.03781","title":"Unifying Uniform and Binary-coding Quantization for Accurate Compression of Large Language Models","created":"2025-06-04","cited_by_count":5},{"id":"2501.12956","title":"GANQ: GPU-Adaptive Non-Uniform Quantization for Large Language Models","created":"2025-01-22","cited_by_count":3},{"id":"2506.03510","title":"Accurate Sublayer Pruning for Large Language Models by Exploiting Latency and Tunability Information","created":"2025-06-04","cited_by_count":2},{"id":"2511.10004","title":"LampQ: Towards Accurate Layer-wise Mixed Precision Quantization for Vision Transformers","created":"2025-11-13","cited_by_count":2}],"next_cursor":null}