{"list":"other","total":111,"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":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"2203.00667","title":"Generative Adversarial Networks","created":"2022-03-01","cited_by_count":5627},{"id":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"1910.01108","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","created":"2019-10-02","cited_by_count":4307},{"id":"1406.1078","title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","created":"2014-06-03","cited_by_count":4057},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"1409.3215","title":"Sequence to Sequence Learning with Neural Networks","created":"2014-09-10","cited_by_count":2986},{"id":"1909.11942","title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations","created":"2019-09-26","cited_by_count":2790},{"id":"2006.03654","title":"DeBERTa: Decoding-enhanced BERT with Disentangled Attention","created":"2020-06-05","cited_by_count":2181},{"id":"2006.16236","title":"Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention","created":"2020-06-29","cited_by_count":2022},{"id":"1901.08746","title":"BioBERT: a pre-trained biomedical language representation model for biomedical text mining","created":"2019-01-25","cited_by_count":1947},{"id":"1901.02860","title":"Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context","created":"2019-01-09","cited_by_count":1850},{"id":"2007.14062","title":"Big Bird: Transformers for Longer Sequences","created":"2020-07-28","cited_by_count":1684},{"id":"2001.04451","title":"Reformer: The Efficient Transformer","created":"2020-01-13","cited_by_count":1668},{"id":"2009.14794","title":"Rethinking Attention with Performers","created":"2020-09-30","cited_by_count":1601},{"id":"1904.10509","title":"Generating Long Sequences with Sparse Transformers","created":"2019-04-23","cited_by_count":1546},{"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":"1502.03044","title":"Show, Attend and Tell: Neural Image Caption Generation with Visual Attention","created":"2015-02-10","cited_by_count":1423},{"id":"1909.10351","title":"TinyBERT: Distilling BERT for Natural Language Understanding","created":"2019-09-23","cited_by_count":1167},{"id":"1803.02155","title":"Self-Attention with Relative Position Representations","created":"2018-03-06","cited_by_count":1120},{"id":"2103.03206","title":"Perceiver: General Perception with Iterative Attention","created":"2021-03-04","cited_by_count":1104},{"id":"1508.04025","title":"Effective Approaches to Attention-based Neural Machine Translation","created":"2015-08-17","cited_by_count":1026},{"id":"1906.04341","title":"What Does BERT Look At? An Analysis of BERT's Attention","created":"2019-06-11","cited_by_count":1003},{"id":"1411.4555","title":"Show and Tell: A Neural Image Caption Generator","created":"2014-11-17","cited_by_count":879},{"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":"1907.10529","title":"SpanBERT: Improving Pre-training by Representing and Predicting Spans","created":"2019-07-24","cited_by_count":834},{"id":"1805.08318","title":"Self-Attention Generative Adversarial Networks","created":"2018-05-21","cited_by_count":809},{"id":"1802.05751","title":"Image Transformer","created":"2018-02-15","cited_by_count":772},{"id":"1807.03819","title":"Universal Transformers","created":"2018-07-10","cited_by_count":647},{"id":"1508.01211","title":"Listen, Attend and Spell","created":"2015-08-05","cited_by_count":543},{"id":"1906.05909","title":"Stand-Alone Self-Attention in Vision Models","created":"2019-06-13","cited_by_count":542},{"id":"1911.06455","title":"Graph Transformer Networks","created":"2019-11-06","cited_by_count":523},{"id":"1908.09355","title":"Patient Knowledge Distillation for BERT Model Compression","created":"2019-08-25","cited_by_count":508},{"id":"2003.05997","title":"Efficient Content-Based Sparse Attention with Routing Transformers","created":"2020-03-12","cited_by_count":471},{"id":"1506.07503","title":"Attention-Based Models for Speech Recognition","created":"2015-06-24","cited_by_count":401},{"id":"1812.01243","title":"Efficient Attention: Attention with Linear Complexities","created":"2018-12-04","cited_by_count":368},{"id":"1705.04304","title":"A Deep Reinforced Model for Abstractive Summarization","created":"2017-05-11","cited_by_count":365},{"id":"1909.05840","title":"Q-BERT: Hessian Based Ultra Low Precision Quantization of BERT","created":"2019-09-12","cited_by_count":359},{"id":"2103.02143","title":"Random Feature Attention","created":"2021-03-03","cited_by_count":354},{"id":"1406.6247","title":"Recurrent Models of Visual Attention","created":"2014-06-24","cited_by_count":349},{"id":"2106.09681","title":"XCiT: Cross-Covariance Image Transformers","created":"2021-06-17","cited_by_count":338},{"id":"1511.03416","title":"Visual7W: Grounded Question Answering in Images","created":"2015-11-11","cited_by_count":318},{"id":"1703.03130","title":"A Structured Self-attentive Sentence Embedding","created":"2017-03-09","cited_by_count":318},{"id":"1910.06188","title":"Q8BERT: Quantized 8Bit BERT","created":"2019-10-14","cited_by_count":300},{"id":"1911.03584","title":"On the Relationship between Self-Attention and Convolutional Layers","created":"2019-11-08","cited_by_count":300},{"id":"1606.00061","title":"Hierarchical Question-Image Co-Attention for Visual Question Answering","created":"2016-05-31","cited_by_count":278},{"id":"1511.02274","title":"Stacked Attention Networks for Image Question Answering","created":"2015-11-07","cited_by_count":273},{"id":"1910.06764","title":"Stabilizing Transformers for Reinforcement Learning","created":"2019-10-13","cited_by_count":270},{"id":"2002.11296","title":"Sparse Sinkhorn Attention","created":"2020-02-26","cited_by_count":251},{"id":"1809.04281","title":"Music Transformer","created":"2018-09-12","cited_by_count":211},{"id":"1502.04623","title":"DRAW: A Recurrent Neural Network For Image Generation","created":"2015-02-16","cited_by_count":191},{"id":"1901.11117","title":"The Evolved Transformer","created":"2019-01-30","cited_by_count":180},{"id":"1804.09541","title":"QANet: Combining Local Convolution with Global Self-Attention for Reading Comprehension","created":"2018-04-23","cited_by_count":164},{"id":"1909.00015","title":"Adaptively Sparse Transformers","created":"2019-08-30","cited_by_count":155},{"id":"2105.02605","title":"GraphFormers: GNN-nested Transformers for Representation Learning on Textual Graph","created":"2021-05-06","cited_by_count":143},{"id":"1808.04444","title":"Character-Level Language Modeling with Deeper Self-Attention","created":"2018-08-09","cited_by_count":138},{"id":"1511.02793","title":"Generating Images from Captions with Attention","created":"2015-11-09","cited_by_count":136},{"id":"1810.00825","title":"Set Transformer: A Framework for Attention-based Permutation-Invariant Neural Networks","created":"2018-10-01","cited_by_count":132},{"id":"2110.11945","title":"SOFT: Softmax-free Transformer with Linear Complexity","created":"2021-10-22","cited_by_count":128},{"id":"2004.11886","title":"Lite Transformer with Long-Short Range Attention","created":"2020-04-24","cited_by_count":127},{"id":"1908.09091","title":"BERT for Coreference Resolution: Baselines and Analysis","created":"2019-08-24","cited_by_count":125},{"id":"1904.02874","title":"An Attentive Survey of Attention Models","created":"2019-04-05","cited_by_count":124},{"id":"2007.04825","title":"Fast Transformers with Clustered Attention","created":"2020-07-09","cited_by_count":123},{"id":"1908.04211","title":"On Identifiability in Transformers","created":"2019-08-12","cited_by_count":116},{"id":"1908.04577","title":"StructBERT: Incorporating Language Structures into Pre-training for Deep Language Understanding","created":"2019-08-13","cited_by_count":109},{"id":"1610.02454","title":"Learning What and Where to Draw","created":"2016-10-08","cited_by_count":105},{"id":"1811.01727","title":"AttentionXML: Label Tree-based Attention-Aware Deep Model for High-Performance Extreme Multi-Label Text Classification","created":"2018-11-01","cited_by_count":102},{"id":"2107.02192","title":"Long-Short Transformer: Efficient Transformers for Language and Vision","created":"2021-07-05","cited_by_count":102},{"id":"1902.02181","title":"Attention in Natural Language Processing","created":"2019-02-04","cited_by_count":101},{"id":"2106.01540","title":"Luna: Linear Unified Nested Attention","created":"2021-06-03","cited_by_count":96},{"id":"2002.07028","title":"Low-Rank Bottleneck in Multi-head Attention Models","created":"2020-02-17","cited_by_count":89},{"id":"1706.05137","title":"One Model To Learn Them All","created":"2017-06-16","cited_by_count":87},{"id":"1906.09777","title":"A Tensorized Transformer for Language Modeling","created":"2019-06-24","cited_by_count":86},{"id":"2103.10619","title":"Scalable Vision Transformers with Hierarchical Pooling","created":"2021-03-19","cited_by_count":84},{"id":"2002.11794","title":"Train Large, Then Compress: Rethinking Model Size for Efficient Training and Inference of Transformers","created":"2020-02-26","cited_by_count":67},{"id":"1511.05234","title":"Ask, Attend and Answer: Exploring Question-Guided Spatial Attention for Visual Question Answering","created":"2015-11-17","cited_by_count":66},{"id":"2002.03830","title":"Attentive Group Equivariant Convolutional Networks","created":"2020-02-07","cited_by_count":63},{"id":"2111.00035","title":"Skyformer: Remodel Self-Attention with Gaussian Kernel and Nystr\\\"om Method","created":"2021-10-29","cited_by_count":63},{"id":"2003.09229","title":"Learning to Encode Position for Transformer with Continuous Dynamical Model","created":"2020-03-13","cited_by_count":61},{"id":"1903.08788","title":"Selective Attention for Context-aware Neural Machine Translation","created":"2019-03-21","cited_by_count":60},{"id":"1706.06122","title":"VAIN: Attentional Multi-agent Predictive Modeling","created":"2017-06-19","cited_by_count":53},{"id":"2010.10604","title":"Bayesian Attention Modules","created":"2020-10-20","cited_by_count":51},{"id":"2106.12566","title":"Stable, Fast and Accurate: Kernelized Attention with Relative Positional Encoding","created":"2021-06-23","cited_by_count":51},{"id":"1511.04119","title":"Action Recognition using Visual Attention","created":"2015-11-12","cited_by_count":49},{"id":"1810.10182","title":"Modeling Localness for Self-Attention Networks","created":"2018-10-24","cited_by_count":43},{"id":"2106.02277","title":"Glance-and-Gaze Vision Transformer","created":"2021-06-04","cited_by_count":42},{"id":"1807.07984","title":"Attention Models in Graphs: A Survey","created":"2018-07-20","cited_by_count":41},{"id":"2101.08001","title":"UPDeT: Universal Multi-agent Reinforcement Learning via Policy Decoupling with Transformers","created":"2021-01-20","cited_by_count":39},{"id":"1512.05193","title":"ABCNN: Attention-Based Convolutional Neural Network for Modeling Sentence Pairs","created":"2015-12-16","cited_by_count":35},{"id":"1912.05537","title":"Encoding Musical Style with Transformer Autoencoders","created":"2019-12-10","cited_by_count":35},{"id":"2104.01655","title":"Efficient Transformers in Reinforcement Learning using Actor-Learner Distillation","created":"2021-04-04","cited_by_count":35},{"id":"2002.03519","title":"Self-Attentive Associative Memory","created":"2020-02-10","cited_by_count":33},{"id":"1904.03092","title":"Modeling Recurrence for Transformer","created":"2019-04-05","cited_by_count":26},{"id":"2108.02347","title":"FMMformer: Efficient and Flexible Transformer via Decomposed Near-field and Far-field Attention","created":"2021-08-05","cited_by_count":26},{"id":"1902.05766","title":"Context-Aware Self-Attention Networks","created":"2019-02-15","cited_by_count":25},{"id":"1511.05960","title":"ABC-CNN: An Attention Based Convolutional Neural Network for Visual Question Answering","created":"2015-11-18","cited_by_count":24}],"next_cursor":"100"}