{"list":"other","total":54,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"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":"1910.01108","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","created":"2019-10-02","cited_by_count":4307},{"id":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"id":"1609.07843","title":"Pointer Sentinel Mixture Models","created":"2016-09-26","cited_by_count":3096},{"id":"1704.05426","title":"A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference","created":"2017-04-18","cited_by_count":2682},{"id":"1506.02626","title":"Learning both Weights and Connections for Efficient Neural Networks","created":"2015-06-08","cited_by_count":2031},{"id":"1412.6550","title":"FitNets: Hints for Thin Deep Nets","created":"2014-12-19","cited_by_count":1653},{"id":"2002.10957","title":"MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers","created":"2020-02-25","cited_by_count":1463},{"id":"1909.10351","title":"TinyBERT: Distilling BERT for Natural Language Understanding","created":"2019-09-23","cited_by_count":1167},{"id":"2301.00774","title":"SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot","created":"2023-01-02","cited_by_count":1121},{"id":"1906.04341","title":"What Does BERT Look At? An Analysis of BERT's Attention","created":"2019-06-11","cited_by_count":1003},{"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":"1805.12471","title":"Neural Network Acceptability Judgments","created":"2018-05-31","cited_by_count":958},{"id":"1612.00410","title":"Deep Variational Information Bottleneck","created":"2016-12-01","cited_by_count":930},{"id":"1905.09418","title":"Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned","created":"2019-05-23","cited_by_count":856},{"id":"1905.10650","title":"Are Sixteen Heads Really Better than One?","created":"2019-05-25","cited_by_count":816},{"id":"1503.02406","title":"Deep Learning and the Information Bottleneck Principle","created":"2015-03-09","cited_by_count":802},{"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":"1710.01878","title":"To prune, or not to prune: exploring the efficacy of pruning for model compression","created":"2017-10-05","cited_by_count":603},{"id":"1908.09355","title":"Patient Knowledge Distillation for BERT Model Compression","created":"2019-08-25","cited_by_count":508},{"id":"2004.02984","title":"MobileBERT: a Compact Task-Agnostic BERT for Resource-Limited Devices","created":"2020-04-06","cited_by_count":482},{"id":"1909.11556","title":"Reducing Transformer Depth on Demand with Structured Dropout","created":"2019-09-25","cited_by_count":439},{"id":"2005.07683","title":"Movement Pruning: Adaptive Sparsity by Fine-Tuning","created":"2020-05-15","cited_by_count":403},{"id":"1910.06188","title":"Q8BERT: Quantized 8Bit BERT","created":"2019-10-14","cited_by_count":300},{"id":"2101.01321","title":"I-BERT: Integer-only BERT Quantization","created":"2021-01-05","cited_by_count":255},{"id":"2004.04037","title":"DynaBERT: Dynamic BERT with Adaptive Width and Depth","created":"2020-04-08","cited_by_count":251},{"id":"2012.15828","title":"MiniLMv2: Multi-Head Self-Attention Relation Distillation for Compressing Pretrained Transformers","created":"2020-12-31","cited_by_count":245},{"id":"2003.02389","title":"Comparing Rewinding and Fine-tuning in Neural Network Pruning","created":"2020-03-05","cited_by_count":240},{"id":"1910.04732","title":"Structured Pruning of Large Language Models","created":"2019-10-10","cited_by_count":203},{"id":"2012.15701","title":"BinaryBERT: Pushing the Limit of BERT Quantization","created":"2020-12-31","cited_by_count":178},{"id":"2109.04838","title":"Block Pruning For Faster Transformers","created":"2021-09-10","cited_by_count":177},{"id":"2204.00408","title":"Structured Pruning Learns Compact and Accurate Models","created":"2022-04-01","cited_by_count":170},{"id":"2204.09656","title":"A Fast Post-Training Pruning Framework for Transformers","created":"2022-03-29","cited_by_count":162},{"id":"1903.12136","title":"Distilling Task-Specific Knowledge from BERT into Simple Neural Networks","created":"2019-03-28","cited_by_count":153},{"id":"2306.11222","title":"LoSparse: Structured Compression of Large Language Models based on Low-Rank and Sparse Approximation","created":"2023-06-20","cited_by_count":104},{"id":"2210.01351","title":"Less is More: Task-aware Layer-wise Distillation for Language Model Compression","created":"2022-10-04","cited_by_count":93},{"id":"1910.03723","title":"Knowledge Distillation from Internal Representations","created":"2019-10-08","cited_by_count":87},{"id":"2111.05754","title":"Prune Once for All: Sparse Pre-Trained Language Models","created":"2021-11-10","cited_by_count":66},{"id":"1802.10399","title":"Compressing Neural Networks using the Variational Information Bottleneck","created":"2018-02-28","cited_by_count":59},{"id":"2105.12002","title":"Super Tickets in Pre-Trained Language Models: From Model Compression to Improving Generalization","created":"2021-05-25","cited_by_count":56},{"id":"2402.05406","title":"Everybody Prune Now: Structured Pruning of LLMs with only Forward Passes","created":"2024-02-08","cited_by_count":43},{"id":"2302.09632","title":"HomoDistil: Homotopic Task-Agnostic Distillation of Pre-trained Transformers","created":"2023-02-19","cited_by_count":25},{"id":"2106.02834","title":"MergeDistill: Merging Pre-trained Language Models using Distillation","created":"2021-06-05","cited_by_count":13},{"id":"2010.01343","title":"A Variational Information Bottleneck Based Method to Compress Sequential Networks for Human Action Recognition","created":"2020-10-03","cited_by_count":7},{"id":"2205.04157","title":"Task-specific Compression for Multi-task Language Models using Attribution-based Pruning","created":"2022-05-09","cited_by_count":7},{"id":"2104.11928","title":"Extract then Distill: Efficient and Effective Task-Agnostic BERT Distillation","created":"2021-04-24","cited_by_count":6},{"id":"2207.13529","title":"A Variational AutoEncoder for Transformers with Nonparametric Variational Information Bottleneck","created":"2022-07-27","cited_by_count":3},{"id":"2307.04443","title":"Search-time Efficient Device Constraints-Aware Neural Architecture Search","created":"2023-07-10","cited_by_count":3},{"id":"2306.05785","title":"End-to-End Neural Network Compression via $\\frac{\\ell_1}{\\ell_2}$ Regularized Latency Surrogates","created":"2023-06-09","cited_by_count":1}],"next_cursor":null}