{"list":"other","total":55,"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":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1802.05365","title":"Deep contextualized word representations","created":"2018-02-15","cited_by_count":2290},{"id":"1804.08771","title":"A Call for Clarity in Reporting BLEU Scores","created":"2018-04-23","cited_by_count":1799},{"id":"1904.01038","title":"fairseq: A Fast, Extensible Toolkit for Sequence Modeling","created":"2019-04-01","cited_by_count":1488},{"id":"1704.04368","title":"Get To The Point: Summarization with Pointer-Generator Networks","created":"2017-04-14","cited_by_count":1292},{"id":"1807.11164","title":"ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design","created":"2018-07-30","cited_by_count":1136},{"id":"2001.08210","title":"Multilingual Denoising Pre-training for Neural Machine Translation","created":"2020-01-22","cited_by_count":1035},{"id":"1906.04341","title":"What Does BERT Look At? An Analysis of BERT's Attention","created":"2019-06-11","cited_by_count":1003},{"id":"2103.15808","title":"CvT: Introducing Convolutions to Vision Transformers","created":"2021-03-29","cited_by_count":947},{"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":"2103.17239","title":"Going deeper with Image Transformers","created":"2021-03-31","cited_by_count":764},{"id":"1705.03122","title":"Convolutional Sequence to Sequence Learning","created":"2017-05-08","cited_by_count":552},{"id":"2103.03404","title":"Attention is Not All You Need: Pure Attention Loses Rank Doubly Exponentially with Depth","created":"2021-03-05","cited_by_count":419},{"id":"2106.14881","title":"Early Convolutions Help Transformers See Better","created":"2021-06-28","cited_by_count":396},{"id":"1906.01787","title":"Learning Deep Transformer Models for Machine Translation","created":"2019-06-05","cited_by_count":309},{"id":"2103.11886","title":"DeepViT: Towards Deeper Vision Transformer","created":"2021-03-22","cited_by_count":289},{"id":"1809.10853","title":"Adaptive Input Representations for Neural Language Modeling","created":"2018-09-28","cited_by_count":226},{"id":"1808.10792","title":"Bottom-Up Abstractive Summarization","created":"2018-08-31","cited_by_count":177},{"id":"2105.03889","title":"Conformer: Local Features Coupling Global Representations for Visual Recognition","created":"2021-05-09","cited_by_count":164},{"id":"1304.5634","title":"A Survey on Multi-view Learning","created":"2013-04-20","cited_by_count":152},{"id":"1905.07799","title":"Adaptive Attention Span in Transformers","created":"2019-05-19","cited_by_count":149},{"id":"2203.05962","title":"Anti-Oversmoothing in Deep Vision Transformers via the Fourier Domain Analysis: From Theory to Practice","created":"2022-03-09","cited_by_count":136},{"id":"2210.06681","title":"Brain Network Transformer","created":"2022-10-13","cited_by_count":94},{"id":"1909.02480","title":"FlowSeq: Non-Autoregressive Conditional Sequence Generation with Generative Flow","created":"2019-09-05","cited_by_count":89},{"id":"2002.07028","title":"Low-Rank Bottleneck in Multi-head Attention Models","created":"2020-02-17","cited_by_count":89},{"id":"2110.09456","title":"NormFormer: Improved Transformer Pretraining with Extra Normalization","created":"2021-10-18","cited_by_count":83},{"id":"1606.02891","title":"Edinburgh Neural Machine Translation Systems for WMT 16","created":"2016-06-09","cited_by_count":76},{"id":"2111.14556","title":"On the Integration of Self-Attention and Convolution","created":"2021-11-29","cited_by_count":74},{"id":"2202.08625","title":"Revisiting Over-smoothing in BERT from the Perspective of Graph","created":"2022-02-17","cited_by_count":72},{"id":"2003.02436","title":"Talking-Heads Attention","created":"2020-03-05","cited_by_count":62},{"id":"2210.05144","title":"Mixture of Attention Heads: Selecting Attention Heads Per Token","created":"2022-10-11","cited_by_count":60},{"id":"2008.07772","title":"Very Deep Transformers for Neural Machine Translation","created":"2020-08-18","cited_by_count":50},{"id":"2104.12753","title":"Vision Transformers with Patch Diversification","created":"2021-04-26","cited_by_count":45},{"id":"2106.03714","title":"Refiner: Refining Self-attention for Vision Transformers","created":"2021-06-07","cited_by_count":38},{"id":"1801.08831","title":"A Multilayer Convolutional Encoder-Decoder Neural Network for Grammatical Error Correction","created":"2018-01-26","cited_by_count":36},{"id":"2010.03737","title":"Shallow-to-Deep Training for Neural Machine Translation","created":"2020-10-08","cited_by_count":36},{"id":"1810.10183","title":"Multi-Head Attention with Disagreement Regularization","created":"2018-10-24","cited_by_count":35},{"id":"2009.08034","title":"Towards Fully 8-bit Integer Inference for the Transformer Model","created":"2020-09-17","cited_by_count":35},{"id":"1904.03107","title":"Convolutional Self-Attention Networks","created":"2019-04-05","cited_by_count":32},{"id":"2103.13597","title":"Mask Attention Networks: Rethinking and Strengthen Transformer","created":"2021-03-25","cited_by_count":28},{"id":"2203.09176","title":"ODE Transformer: An Ordinary Differential Equation-Inspired Model for Sequence Generation","created":"2022-03-17","cited_by_count":27},{"id":"2012.14768","title":"Understanding and Improving Encoder Layer Fusion in Sequence-to-Sequence Learning","created":"2020-12-29","cited_by_count":26},{"id":"2012.13866","title":"Learning Light-Weight Translation Models from Deep Transformer","created":"2020-12-27","cited_by_count":22},{"id":"1911.09483","title":"MUSE: Parallel Multi-Scale Attention for Sequence to Sequence Learning","created":"2019-11-17","cited_by_count":19},{"id":"2112.12786","title":"ELSA: Enhanced Local Self-Attention for Vision Transformer","created":"2021-12-23","cited_by_count":18},{"id":"1912.00544","title":"Multi-Scale Self-Attention for Text Classification","created":"2019-12-02","cited_by_count":16},{"id":"1904.03100","title":"Information Aggregation for Multi-Head Attention with Routing-by-Agreement","created":"2019-04-05","cited_by_count":13},{"id":"2004.14021","title":"Multiscale Collaborative Deep Models for Neural Machine Translation","created":"2020-04-29","cited_by_count":11},{"id":"1909.02222","title":"Multi-Granularity Self-Attention for Neural Machine Translation","created":"2019-09-05","cited_by_count":10},{"id":"2206.09337","title":"Learning Multiscale Transformer Models for Sequence Generation","created":"2022-06-19","cited_by_count":7}],"next_cursor":null}