{"list":"other","total":61,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"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":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"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":"1301.3781","title":"Efficient Estimation of Word Representations in Vector Space","created":"2013-01-16","cited_by_count":4375},{"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":"1704.04861","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","created":"2017-04-17","cited_by_count":3845},{"id":"1606.08415","title":"Gaussian Error Linear Units (GELUs)","created":"2016-06-27","cited_by_count":3502},{"id":"1310.4546","title":"Distributed Representations of Words and Phrases and their Compositionality","created":"2013-10-16","cited_by_count":3474},{"id":"1906.08237","title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding","created":"2019-06-19","cited_by_count":2811},{"id":"1909.11942","title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations","created":"2019-09-26","cited_by_count":2790},{"id":"1704.05426","title":"A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference","created":"2017-04-18","cited_by_count":2682},{"id":"1802.05365","title":"Deep contextualized word representations","created":"2018-02-15","cited_by_count":2290},{"id":"1806.09055","title":"DARTS: Differentiable Architecture Search","created":"2018-06-24","cited_by_count":1798},{"id":"1806.03822","title":"Know What You Don't Know: Unanswerable Questions for SQuAD","created":"2018-06-11","cited_by_count":1554},{"id":"1909.10351","title":"TinyBERT: Distilling BERT for Natural Language Understanding","created":"2019-09-23","cited_by_count":1167},{"id":"1408.5882","title":"Convolutional Neural Networks for Sentence Classification","created":"2014-08-25","cited_by_count":1127},{"id":"1901.07291","title":"Cross-lingual Language Model Pretraining","created":"2019-01-22","cited_by_count":1090},{"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":"1802.03268","title":"Efficient Neural Architecture Search via Parameter Sharing","created":"2018-02-09","cited_by_count":837},{"id":"1907.10529","title":"SpanBERT: Improving Pre-training by Representing and Predicting Spans","created":"2019-07-24","cited_by_count":834},{"id":"1908.09791","title":"Once-for-All: Train One Network and Specialize it for Efficient Deployment","created":"2019-08-26","cited_by_count":787},{"id":"1612.08083","title":"Language Modeling with Gated Convolutional Networks","created":"2016-12-23","cited_by_count":702},{"id":"1812.00332","title":"ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware","created":"2018-12-02","cited_by_count":673},{"id":"1905.07129","title":"ERNIE: Enhanced Language Representation with Informative Entities","created":"2019-05-17","cited_by_count":528},{"id":"1812.03443","title":"FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search","created":"2018-12-09","cited_by_count":485},{"id":"2004.02984","title":"MobileBERT: a Compact Task-Agnostic BERT for Resource-Limited Devices","created":"2020-04-06","cited_by_count":482},{"id":"1904.00420","title":"Single Path One-Shot Neural Architecture Search with Uniform Sampling","created":"2019-03-31","cited_by_count":414},{"id":"1703.01041","title":"Large-Scale Evolution of Image Classifiers","created":"2017-03-03","cited_by_count":348},{"id":"1909.07606","title":"K-BERT: Enabling Language Representation with Knowledge Graph","created":"2019-09-17","cited_by_count":304},{"id":"1908.08593","title":"Revealing the Dark Secrets of BERT","created":"2019-08-21","cited_by_count":301},{"id":"1909.04164","title":"Knowledge Enhanced Contextual Word Representations","created":"2019-09-09","cited_by_count":296},{"id":"1904.07392","title":"NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detection","created":"2019-04-16","cited_by_count":291},{"id":"1812.09926","title":"SNAS: Stochastic Neural Architecture Search","created":"2018-12-24","cited_by_count":289},{"id":"1611.02167","title":"Designing Neural Network Architectures using Reinforcement Learning","created":"2016-11-07","cited_by_count":279},{"id":"1901.02985","title":"Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation","created":"2019-01-10","cited_by_count":260},{"id":"2006.02903","title":"A Comprehensive Survey of Neural Architecture Search: Challenges and Solutions","created":"2020-06-01","cited_by_count":254},{"id":"1901.10430","title":"Pay Less Attention with Lightweight and Dynamic Convolutions","created":"2019-01-29","cited_by_count":211},{"id":"1708.05344","title":"SMASH: One-Shot Model Architecture Search through HyperNetworks","created":"2017-08-17","cited_by_count":202},{"id":"1901.11117","title":"The Evolved Transformer","created":"2019-01-30","cited_by_count":180},{"id":"1404.2188","title":"A Convolutional Neural Network for Modelling Sentences","created":"2014-04-08","cited_by_count":163},{"id":"2005.14187","title":"HAT: Hardware-Aware Transformers for Efficient Natural Language Processing","created":"2020-05-28","cited_by_count":136},{"id":"2004.11886","title":"Lite Transformer with Long-Short Range Attention","created":"2020-04-24","cited_by_count":127},{"id":"1908.04211","title":"On Identifiability in Transformers","created":"2019-08-12","cited_by_count":116},{"id":"1708.00107","title":"Learned in Translation: Contextualized Word Vectors","created":"2017-08-01","cited_by_count":104},{"id":"1912.09637","title":"Pretrained Encyclopedia: Weakly Supervised Knowledge-Pretrained Language Model","created":"2019-12-20","cited_by_count":102},{"id":"1909.00964","title":"Unicoder: A Universal Language Encoder by Pre-training with Multiple Cross-lingual Tasks","created":"2019-09-03","cited_by_count":96},{"id":"2008.02496","title":"ConvBERT: Improving BERT with Span-based Dynamic Convolution","created":"2020-08-06","cited_by_count":88},{"id":"1909.10481","title":"Cross-Lingual Natural Language Generation via Pre-Training","created":"2019-09-23","cited_by_count":63},{"id":"1911.03864","title":"Improving Transformer Models by Reordering their Sublayers","created":"2019-11-10","cited_by_count":52},{"id":"2001.04246","title":"AdaBERT: Task-Adaptive BERT Compression with Differentiable Neural Architecture Search","created":"2020-01-13","cited_by_count":51},{"id":"2005.06628","title":"schuBERT: Optimizing Elements of BERT","created":"2020-05-09","cited_by_count":17},{"id":"2009.10680","title":"AutoRC: Improving BERT Based Relation Classification Models via Architecture Search","created":"2020-09-22","cited_by_count":9},{"id":"2008.00177","title":"Multi-node Bert-pretraining: Cost-efficient Approach","created":"2020-08-01","cited_by_count":5}],"next_cursor":null}