{"list":"other","total":53,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"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":"1704.05426","title":"A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference","created":"2017-04-18","cited_by_count":2682},{"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":"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":"1806.03822","title":"Know What You Don't Know: Unanswerable Questions for SQuAD","created":"2018-06-11","cited_by_count":1554},{"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":"2111.09543","title":"DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing","created":"2021-11-18","cited_by_count":1254},{"id":"1909.10351","title":"TinyBERT: Distilling BERT for Natural Language Understanding","created":"2019-09-23","cited_by_count":1167},{"id":"1506.06724","title":"Aligning Books and Movies: Towards Story-like Visual Explanations by Watching Movies and Reading Books","created":"2015-06-22","cited_by_count":1043},{"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":"1905.10650","title":"Are Sixteen Heads Really Better than One?","created":"2019-05-25","cited_by_count":816},{"id":"1810.02340","title":"SNIP: Single-shot Network Pruning based on Connection Sensitivity","created":"2018-10-04","cited_by_count":812},{"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":"1902.03393","title":"Improved Knowledge Distillation via Teacher Assistant","created":"2019-02-09","cited_by_count":573},{"id":"1906.10771","title":"Importance Estimation for Neural Network Pruning","created":"2019-06-25","cited_by_count":541},{"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":"2005.07683","title":"Movement Pruning: Adaptive Sparsity by Fine-Tuning","created":"2020-05-15","cited_by_count":403},{"id":"1910.01348","title":"On the Efficacy of Knowledge Distillation","created":"2019-10-03","cited_by_count":381},{"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":"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":"1903.12136","title":"Distilling Task-Specific Knowledge from BERT into Simple Neural Networks","created":"2019-03-28","cited_by_count":153},{"id":"2002.02925","title":"BERT-of-Theseus: Compressing BERT by Progressive Module Replacing","created":"2020-02-07","cited_by_count":113},{"id":"1801.05787","title":"Faster gaze prediction with dense networks and Fisher pruning","created":"2018-01-17","cited_by_count":94},{"id":"1910.03723","title":"Knowledge Distillation from Internal Representations","created":"2019-10-08","cited_by_count":87},{"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":"1904.09149","title":"Knowledge Distillation via Route Constrained Optimization","created":"2019-04-19","cited_by_count":75},{"id":"1909.12778","title":"Global Sparse Momentum SGD for Pruning Very Deep Neural Networks","created":"2019-09-27","cited_by_count":70},{"id":"2111.05754","title":"Prune Once for All: Sparse Pre-Trained Language Models","created":"2021-11-10","cited_by_count":66},{"id":"2011.00593","title":"MixKD: Towards Efficient Distillation of Large-scale Language Models","created":"2020-11-01","cited_by_count":65},{"id":"2106.04570","title":"BERT Learns to Teach: Knowledge Distillation with Meta Learning","created":"2021-06-08","cited_by_count":61},{"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":"2104.08682","title":"Rethinking Network Pruning -- under the Pre-train and Fine-tune Paradigm","created":"2021-04-18","cited_by_count":40},{"id":"2109.11295","title":"Dynamic Knowledge Distillation for Pre-trained Language Models","created":"2021-09-23","cited_by_count":38},{"id":"2009.11839","title":"A Gradient Flow Framework For Analyzing Network Pruning","created":"2020-09-24","cited_by_count":36},{"id":"2010.13382","title":"FastFormers: Highly Efficient Transformer Models for Natural Language Understanding","created":"2020-10-26","cited_by_count":28},{"id":"2110.08532","title":"Pro-KD: Progressive Distillation by Following the Footsteps of the Teacher","created":"2021-10-16","cited_by_count":17},{"id":"2001.05050","title":"On Iterative Neural Network Pruning, Reinitialization, and the Similarity of Masks","created":"2020-01-14","cited_by_count":13},{"id":"2107.09305","title":"Follow Your Path: a Progressive Method for Knowledge Distillation","created":"2021-07-20","cited_by_count":10}],"next_cursor":null}