{"list":"other","total":70,"rows":[{"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":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"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":"1905.07830","title":"HellaSwag: Can a Machine Really Finish Your Sentence?","created":"2019-05-19","cited_by_count":4100},{"id":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512},{"id":"1609.07843","title":"Pointer Sentinel Mixture Models","created":"2016-09-26","cited_by_count":3096},{"id":"1510.00149","title":"Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding","created":"2015-10-01","cited_by_count":2329},{"id":"1905.10044","title":"BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions","created":"2019-05-24","cited_by_count":2183},{"id":"1809.02789","title":"Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering","created":"2018-09-08","cited_by_count":2164},{"id":"1506.02626","title":"Learning both Weights and Connections for Efficient Neural Networks","created":"2015-06-08","cited_by_count":2031},{"id":"2210.17323","title":"GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers","created":"2022-10-31","cited_by_count":1919},{"id":"2404.14219","title":"Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone","created":"2024-04-22","cited_by_count":1917},{"id":"2211.10438","title":"SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models","created":"2022-11-18","cited_by_count":1386},{"id":"2306.00978","title":"AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration","created":"2023-06-01","cited_by_count":1298},{"id":"2301.00774","title":"SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot","created":"2023-01-02","cited_by_count":1121},{"id":"1707.07012","title":"Learning Transferable Architectures for Scalable Image Recognition","created":"2017-07-21","cited_by_count":1101},{"id":"1802.03268","title":"Efficient Neural Architecture Search via Parameter Sharing","created":"2018-02-09","cited_by_count":837},{"id":"1810.02340","title":"SNIP: Single-shot Network Pruning based on Connection Sensitivity","created":"2018-10-04","cited_by_count":812},{"id":"2306.11695","title":"A Simple and Effective Pruning Approach for Large Language Models","created":"2023-06-20","cited_by_count":800},{"id":"2305.11627","title":"LLM-Pruner: On the Structural Pruning of Large Language Models","created":"2023-05-19","cited_by_count":650},{"id":"2401.02385","title":"TinyLlama: An Open-Source Small Language Model","created":"2024-01-04","cited_by_count":618},{"id":"1810.05270","title":"Rethinking the Value of Network Pruning","created":"2018-10-11","cited_by_count":599},{"id":"1712.01312","title":"Learning Sparse Neural Networks through $L_0$ Regularization","created":"2017-12-04","cited_by_count":583},{"id":"2206.01861","title":"ZeroQuant: Efficient and Affordable Post-Training Quantization for Large-Scale Transformers","created":"2022-06-04","cited_by_count":526},{"id":"2006.05467","title":"Pruning neural networks without any data by iteratively conserving synaptic flow","created":"2020-06-09","cited_by_count":479},{"id":"2005.07683","title":"Movement Pruning: Adaptive Sparsity by Fine-Tuning","created":"2020-05-15","cited_by_count":403},{"id":"2401.15024","title":"SliceGPT: Compress Large Language Models by Deleting Rows and Columns","created":"2024-01-26","cited_by_count":385},{"id":"2305.17888","title":"LLM-QAT: Data-Free Quantization Aware Training for Large Language Models","created":"2023-05-29","cited_by_count":324},{"id":"2007.12223","title":"The Lottery Ticket Hypothesis for Pre-trained BERT Networks","created":"2020-07-23","cited_by_count":275},{"id":"2211.02001","title":"Estimating the Carbon Footprint of BLOOM, a 176B Parameter Language Model","created":"2022-11-03","cited_by_count":265},{"id":"1907.10641","title":"WinoGrande: An Adversarial Winograd Schema Challenge at Scale","created":"2019-07-24","cited_by_count":204},{"id":"2301.12900","title":"DepGraph: Towards Any Structural Pruning","created":"2023-01-30","cited_by_count":203},{"id":"2310.05175","title":"Outlier Weighed Layerwise Sparsity (OWL): A Missing Secret Sauce for Pruning LLMs to High Sparsity","created":"2023-10-08","cited_by_count":165},{"id":"2204.09656","title":"A Fast Post-Training Pruning Framework for Transformers","created":"2022-03-29","cited_by_count":162},{"id":"1806.07259","title":"Learning Equations for Extrapolation and Control","created":"2018-06-19","cited_by_count":156},{"id":"2003.03384","title":"AutoML-Zero: Evolving Machine Learning Algorithms From Scratch","created":"2020-03-06","cited_by_count":143},{"id":"2312.13558","title":"The Truth is in There: Improving Reasoning in Language Models with Layer-Selective Rank Reduction","created":"2023-12-21","cited_by_count":123},{"id":"1507.06149","title":"Data-free parameter pruning for Deep Neural Networks","created":"2015-07-22","cited_by_count":112},{"id":"1610.02995","title":"Extrapolation and learning equations","created":"2016-10-10","cited_by_count":110},{"id":"2012.09243","title":"Neural Pruning via Growing Regularization","created":"2020-12-16","cited_by_count":97},{"id":"2206.12562","title":"PLATON: Pruning Large Transformer Models with Upper Confidence Bound of Weight Importance","created":"2022-06-25","cited_by_count":79},{"id":"2402.18158","title":"Evaluating Quantized Large Language Models","created":"2024-02-28","cited_by_count":77},{"id":"2207.01018","title":"Symbolic Regression is NP-hard","created":"2022-07-03","cited_by_count":71},{"id":"2310.16836","title":"LLM-FP4: 4-Bit Floating-Point Quantized Transformers","created":"2023-10-25","cited_by_count":69},{"id":"2402.16880","title":"BESA: Pruning Large Language Models with Blockwise Parameter-Efficient Sparsity Allocation","created":"2024-02-18","cited_by_count":45},{"id":"2305.13803","title":"NORM: Knowledge Distillation via N-to-One Representation Matching","created":"2023-05-23","cited_by_count":44},{"id":"2312.17244","title":"The LLM Surgeon","created":"2023-12-28","cited_by_count":38},{"id":"2202.12002","title":"Rare Gems: Finding Lottery Tickets at Initialization","created":"2022-02-24","cited_by_count":34},{"id":"2303.06862","title":"OTOV2: Automatic, Generic, User-Friendly","created":"2023-03-13","cited_by_count":32},{"id":"2311.04902","title":"Beyond Size: How Gradients Shape Pruning Decisions in Large Language Models","created":"2023-11-08","cited_by_count":30},{"id":"2303.15678","title":"DisWOT: Student Architecture Search for Distillation WithOut Training","created":"2023-03-28","cited_by_count":29},{"id":"2302.05601","title":"Pruning Deep Neural Networks from a Sparsity Perspective","created":"2023-02-11","cited_by_count":25},{"id":"2307.10554","title":"EMQ: Evolving Training-free Proxies for Automated Mixed Precision Quantization","created":"2023-07-20","cited_by_count":22},{"id":"2106.09269","title":"Pruning Randomly Initialized Neural Networks with Iterative Randomization","created":"2021-06-17","cited_by_count":20},{"id":"2309.01172","title":"FusionAI: Decentralized Training and Deploying LLMs with Massive Consumer-Level GPUs","created":"2023-09-03","cited_by_count":20},{"id":"2110.01397","title":"RED++ : Data-Free Pruning of Deep Neural Networks via Input Splitting and Output Merging","created":"2021-09-30","cited_by_count":19},{"id":"2209.07413","title":"EZNAS: Evolving Zero Cost Proxies For Neural Architecture Scoring","created":"2022-09-15","cited_by_count":15},{"id":"2402.07011","title":"FedImpro: Measuring and Improving Client Update in Federated Learning","created":"2024-02-10","cited_by_count":15},{"id":"2312.15230","title":"PERP: Rethinking the Prune-Retrain Paradigm in the Era of LLMs","created":"2023-12-23","cited_by_count":14},{"id":"2312.09059","title":"Auto-Prox: Training-Free Vision Transformer Architecture Search via Automatic Proxy Discovery","created":"2023-12-14","cited_by_count":13},{"id":"2206.13329","title":"Prior-Guided One-shot Neural Architecture Search","created":"2022-06-27","cited_by_count":12},{"id":"2212.07634","title":"Gradient-based Intra-attention Pruning on Pre-trained Language Models","created":"2022-12-15","cited_by_count":9},{"id":"2402.09773","title":"NutePrune: Efficient Progressive Pruning with Numerous Teachers for Large Language Models","created":"2024-02-15","cited_by_count":7},{"id":"2211.12759","title":"NAS-LID: Efficient Neural Architecture Search with Local Intrinsic Dimension","created":"2022-11-23","cited_by_count":5},{"id":"2402.02105","title":"ParZC: Parametric Zero-Cost Proxies for Efficient NAS","created":"2024-02-03","cited_by_count":5},{"id":"2311.14337","title":"TVT: Training-Free Vision Transformer Search on Tiny Datasets","created":"2023-11-24","cited_by_count":3},{"id":"2305.12394","title":"Pruning Pre-trained Language Models with Principled Importance and Self-regularization","created":"2023-05-21","cited_by_count":2}],"next_cursor":null}