{"list":"other","total":56,"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":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"id":"1710.10903","title":"Graph Attention Networks","created":"2017-10-30","cited_by_count":8923},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1603.02754","title":"XGBoost: A Scalable Tree Boosting System","created":"2016-03-09","cited_by_count":5166},{"id":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"1810.00826","title":"How Powerful are Graph Neural Networks?","created":"2018-10-01","cited_by_count":4393},{"id":"2004.05150","title":"Longformer: The Long-Document Transformer","created":"2020-04-10","cited_by_count":3413},{"id":"1606.04080","title":"Matching Networks for One Shot Learning","created":"2016-06-13","cited_by_count":2255},{"id":"2012.07805","title":"Extracting Training Data from Large Language Models","created":"2020-12-14","cited_by_count":2189},{"id":"2002.08909","title":"REALM: Retrieval-Augmented Language Model Pre-Training","created":"2020-02-10","cited_by_count":2141},{"id":"2006.16236","title":"Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention","created":"2020-06-29","cited_by_count":2022},{"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":"2103.03206","title":"Perceiver: General Perception with Iterative Attention","created":"2021-03-04","cited_by_count":1104},{"id":"1707.02968","title":"Revisiting Unreasonable Effectiveness of Data in Deep Learning Era","created":"2017-07-10","cited_by_count":919},{"id":"2006.15055","title":"Object-Centric Learning with Slot Attention","created":"2020-06-26","cited_by_count":876},{"id":"2009.06732","title":"Efficient Transformers: A Survey","created":"2020-09-14","cited_by_count":790},{"id":"1802.05751","title":"Image Transformer","created":"2018-02-15","cited_by_count":772},{"id":"1912.11370","title":"Big Transfer (BiT): General Visual Representation Learning","created":"2019-12-24","cited_by_count":769},{"id":"1904.00962","title":"Large Batch Optimization for Deep Learning: Training BERT in 76 minutes","created":"2019-04-01","cited_by_count":674},{"id":"1908.07442","title":"TabNet: Attentive Interpretable Tabular Learning","created":"2019-08-20","cited_by_count":648},{"id":"2104.10972","title":"ImageNet-21K Pretraining for the Masses","created":"2021-04-22","cited_by_count":613},{"id":"2006.10503","title":"SE(3)-Transformers: 3D Roto-Translation Equivariant Attention Networks","created":"2020-06-18","cited_by_count":607},{"id":"1406.5298","title":"Semi-Supervised Learning with Deep Generative Models","created":"2014-06-20","cited_by_count":496},{"id":"1511.02222","title":"Deep Kernel Learning","created":"2015-11-06","cited_by_count":445},{"id":"1807.01613","title":"Conditional Neural Processes","created":"2018-07-04","cited_by_count":426},{"id":"1912.12180","title":"Axial Attention in Multidimensional Transformers","created":"2019-12-20","cited_by_count":358},{"id":"1802.04687","title":"Neural Relational Inference for Interacting Systems","created":"2018-02-13","cited_by_count":339},{"id":"1907.08610","title":"Lookahead Optimizer: k steps forward, 1 step back","created":"2019-07-19","cited_by_count":336},{"id":"1711.04043","title":"Few-Shot Learning with Graph Neural Networks","created":"2017-11-10","cited_by_count":324},{"id":"1810.11921","title":"AutoInt: Automatic Feature Interaction Learning via Self-Attentive Neural Networks","created":"2018-10-29","cited_by_count":320},{"id":"1901.05761","title":"Attentive Neural Processes","created":"2019-01-17","cited_by_count":283},{"id":"1703.07464","title":"No Fuss Distance Metric Learning using Proxies","created":"2017-03-21","cited_by_count":226},{"id":"1906.06423","title":"Fixing the train-test resolution discrepancy","created":"2019-06-14","cited_by_count":209},{"id":"1806.03836","title":"Bayesian Model-Agnostic Meta-Learning","created":"2018-06-11","cited_by_count":194},{"id":"1705.08933","title":"Doubly Stochastic Variational Inference for Deep Gaussian Processes","created":"2017-05-24","cited_by_count":143},{"id":"2003.07554","title":"A Unified View of Label Shift Estimation","created":"2020-03-17","cited_by_count":119},{"id":"1804.09849","title":"The Best of Both Worlds: Combining Recent Advances in Neural Machine Translation","created":"2018-04-26","cited_by_count":102},{"id":"2012.10885","title":"LieTransformer: Equivariant self-attention for Lie Groups","created":"2020-12-20","cited_by_count":100},{"id":"1709.08878","title":"Generating Sentences by Editing Prototypes","created":"2017-09-26","cited_by_count":88},{"id":"2102.11972","title":"Do Transformer Modifications Transfer Across Implementations and Applications?","created":"2021-02-23","cited_by_count":87},{"id":"1903.03238","title":"Ranked List Loss for Deep Metric Learning","created":"2019-03-08","cited_by_count":77},{"id":"1812.01194","title":"A Retrieve-and-Edit Framework for Predicting Structured Outputs","created":"2018-12-04","cited_by_count":73},{"id":"1912.10481","title":"A Systematic Comparison of Bayesian Deep Learning Robustness in Diabetic Retinopathy Tasks","created":"2019-12-22","cited_by_count":62},{"id":"1809.07572","title":"Challenges for Toxic Comment Classification: An In-Depth Error Analysis","created":"2018-09-20","cited_by_count":56},{"id":"1811.06817","title":"Evaluating Uncertainty Quantification in End-to-End Autonomous Driving Control","created":"2018-11-16","cited_by_count":55},{"id":"1602.04133","title":"Deep Gaussian Processes for Regression using Approximate Expectation Propagation","created":"2016-02-12","cited_by_count":39},{"id":"2102.07753","title":"Learning Intra-Batch Connections for Deep Metric Learning","created":"2021-02-15","cited_by_count":34},{"id":"1511.06455","title":"Variational Auto-encoded Deep Gaussian Processes","created":"2015-11-19","cited_by_count":20}],"next_cursor":null}