{"list":"other","total":91,"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":"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":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"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":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"id":"1312.6114","title":"Auto-Encoding Variational Bayes","created":"2013-12-20","cited_by_count":4053},{"id":"1310.4546","title":"Distributed Representations of Words and Phrases and their Compositionality","created":"2013-10-16","cited_by_count":3474},{"id":"1312.5602","title":"Playing Atari with Deep Reinforcement Learning","created":"2013-12-19","cited_by_count":3274},{"id":"2101.03961","title":"Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity","created":"2021-01-11","cited_by_count":3073},{"id":"1409.3215","title":"Sequence to Sequence Learning with Neural Networks","created":"2014-09-10","cited_by_count":2986},{"id":"1903.12261","title":"Benchmarking Neural Network Robustness to Common Corruptions and Perturbations","created":"2019-03-28","cited_by_count":2877},{"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":"1602.01783","title":"Asynchronous Methods for Deep Reinforcement Learning","created":"2016-02-04","cited_by_count":2258},{"id":"1311.3618","title":"Describing Textures in the Wild","created":"2013-11-14","cited_by_count":2125},{"id":"2006.16241","title":"The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization","created":"2020-06-29","cited_by_count":1850},{"id":"1508.05326","title":"A large annotated corpus for learning natural language inference","created":"2015-08-21","cited_by_count":1847},{"id":"1509.06461","title":"Deep Reinforcement Learning with Double Q-learning","created":"2015-09-22","cited_by_count":1745},{"id":"1905.00537","title":"SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems","created":"2019-05-02","cited_by_count":1729},{"id":"1806.03822","title":"Know What You Don't Know: Unanswerable Questions for SQuAD","created":"2018-06-11","cited_by_count":1554},{"id":"1902.10811","title":"Do ImageNet Classifiers Generalize to ImageNet?","created":"2019-02-13","cited_by_count":1515},{"id":"1709.00029","title":"EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classification","created":"2017-08-31","cited_by_count":1496},{"id":"1612.06890","title":"CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning","created":"2016-12-20","cited_by_count":1457},{"id":"1907.07174","title":"Natural Adversarial Examples","created":"2019-07-16","cited_by_count":1408},{"id":"1708.05031","title":"Neural Collaborative Filtering","created":"2017-08-16","cited_by_count":1111},{"id":"1801.00690","title":"DeepMind Control Suite","created":"2018-01-02","cited_by_count":956},{"id":"1703.00121","title":"Remote Sensing Image Scene Classification: Benchmark and State of the Art","created":"2017-03-01","cited_by_count":797},{"id":"1511.06581","title":"Dueling Network Architectures for Deep Reinforcement Learning","created":"2015-11-20","cited_by_count":785},{"id":"1912.11370","title":"Big Transfer (BiT): General Visual Representation Learning","created":"2019-12-24","cited_by_count":769},{"id":"1709.06560","title":"Deep Reinforcement Learning that Matters","created":"2017-09-19","cited_by_count":754},{"id":"2003.11080","title":"XTREME: A Massively Multilingual Multi-task Benchmark for Evaluating Cross-lingual Generalization","created":"2020-03-24","cited_by_count":742},{"id":"2011.04006","title":"Long Range Arena: A Benchmark for Efficient Transformers","created":"2020-11-08","cited_by_count":700},{"id":"1803.02324","title":"Annotation Artifacts in Natural Language Inference Data","created":"2018-03-06","cited_by_count":671},{"id":"1807.03819","title":"Universal Transformers","created":"2018-07-10","cited_by_count":647},{"id":"2106.10270","title":"How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers","created":"2021-06-18","cited_by_count":569},{"id":"1602.01585","title":"Ups and Downs: Modeling the Visual Evolution of Fashion Trends with One-Class Collaborative Filtering","created":"2016-02-04","cited_by_count":520},{"id":"2104.14337","title":"Dynabench: Rethinking Benchmarking in NLP","created":"2021-04-07","cited_by_count":459},{"id":"1910.04867","title":"A Large-scale Study of Representation Learning with the Visual Task Adaptation Benchmark","created":"2019-10-01","cited_by_count":425},{"id":"1806.03962","title":"Rotation Equivariant CNNs for Digital Pathology","created":"2018-06-08","cited_by_count":422},{"id":"1611.05397","title":"Reinforcement Learning with Unsupervised Auxiliary Tasks","created":"2016-11-16","cited_by_count":404},{"id":"2103.14749","title":"Pervasive Label Errors in Test Sets Destabilize Machine Learning Benchmarks","created":"2021-03-26","cited_by_count":395},{"id":"1711.01558","title":"Wasserstein Auto-Encoders","created":"2017-11-05","cited_by_count":373},{"id":"1611.01368","title":"Assessing the Ability of LSTMs to Learn Syntax-Sensitive Dependencies","created":"2016-11-04","cited_by_count":354},{"id":"2006.07159","title":"Are we done with ImageNet?","created":"2020-06-12","cited_by_count":333},{"id":"2003.08505","title":"A Metric Learning Reality Check","created":"2020-03-18","cited_by_count":321},{"id":"1904.12901","title":"Challenges of Real-World Reinforcement Learning","created":"2019-04-29","cited_by_count":291},{"id":"1709.06009","title":"Revisiting the Arcade Learning Environment: Evaluation Protocols and Open Problems for General Agents","created":"2017-09-18","cited_by_count":269},{"id":"2102.01672","title":"The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics","created":"2021-02-02","cited_by_count":239},{"id":"2005.00743","title":"Synthesizer: Rethinking Self-Attention in Transformer Models","created":"2020-05-02","cited_by_count":205},{"id":"1810.05934","title":"A System for Massively Parallel Hyperparameter Tuning","created":"2018-10-13","cited_by_count":202},{"id":"2103.03098","title":"Accounting for Variance in Machine Learning Benchmarks","created":"2021-03-01","cited_by_count":201},{"id":"1806.00451","title":"Do CIFAR-10 Classifiers Generalize to CIFAR-10?","created":"2018-06-01","cited_by_count":200},{"id":"1907.06902","title":"Are We Really Making Much Progress? A Worrying Analysis of Recent Neural Recommendation Approaches","created":"2019-07-16","cited_by_count":185},{"id":"1901.11117","title":"The Evolved Transformer","created":"2019-01-30","cited_by_count":180},{"id":"1909.03004","title":"Show Your Work: Improved Reporting of Experimental Results","created":"2019-09-06","cited_by_count":169},{"id":"1707.02286","title":"Emergence of Locomotion Behaviours in Rich Environments","created":"2017-07-07","cited_by_count":165},{"id":"2009.06489","title":"The Hardware Lottery","created":"2020-09-14","cited_by_count":160},{"id":"2103.07579","title":"Revisiting ResNets: Improved Training and Scaling Strategies","created":"2021-03-13","cited_by_count":158},{"id":"1703.01988","title":"Neural Episodic Control","created":"2017-03-06","cited_by_count":151},{"id":"2005.09683","title":"Neural Collaborative Filtering vs. Matrix Factorization Revisited","created":"2020-05-19","cited_by_count":123},{"id":"1807.03341","title":"Troubling Trends in Machine Learning Scholarship","created":"2018-07-09","cited_by_count":108},{"id":"1605.04812","title":"Off-policy evaluation for slate recommendation","created":"2016-05-16","cited_by_count":103},{"id":"1708.05024","title":"Fast Matrix Factorization for Online Recommendation with Implicit Feedback","created":"2017-08-16","cited_by_count":101},{"id":"2104.06294","title":"Online and Offline Reinforcement Learning by Planning with a Learned Model","created":"2021-04-13","cited_by_count":90},{"id":"1507.04296","title":"Massively Parallel Methods for Deep Reinforcement Learning","created":"2015-07-15","cited_by_count":82},{"id":"2106.15195","title":"Scientific Credibility of Machine Translation Research: A Meta-Evaluation of 769 Papers","created":"2021-06-29","cited_by_count":71},{"id":"1502.04585","title":"The Ladder: A Reliable Leaderboard for Machine Learning Competitions","created":"2015-02-16","cited_by_count":69},{"id":"1905.10498","title":"Cold Case: The Lost MNIST Digits","created":"2019-05-25","cited_by_count":62},{"id":"2106.00840","title":"Comparing Test Sets with Item Response Theory","created":"2021-06-01","cited_by_count":57},{"id":"1706.08090","title":"Count-Based Exploration in Feature Space for Reinforcement Learning","created":"2017-06-25","cited_by_count":49},{"id":"1806.02643","title":"Re-evaluating Evaluation","created":"2018-06-07","cited_by_count":47},{"id":"2007.07399","title":"Bringing the People Back In: Contesting Benchmark Machine Learning Datasets","created":"2020-07-14","cited_by_count":43},{"id":"1803.03585","title":"The Importance of Being Recurrent for Modeling Hierarchical Structure","created":"2018-03-09","cited_by_count":42},{"id":"2006.00555","title":"Transferring Inductive Biases through Knowledge Distillation","created":"2020-05-31","cited_by_count":41},{"id":"2010.15982","title":"A Model of Two Tales: Dual Transfer Learning Framework for Improved Long-tail Item Recommendation","created":"2020-10-29","cited_by_count":38},{"id":"1709.09500","title":"Replicability Analysis for Natural Language Processing: Testing Significance with Multiple Datasets","created":"2017-09-27","cited_by_count":32},{"id":"1912.02783","title":"Self-Supervised Learning of Video-Induced Visual Invariances","created":"2019-12-05","cited_by_count":29},{"id":"2106.05532","title":"How Robust are Model Rankings: A Leaderboard Customization Approach for Equitable Evaluation","created":"2021-06-10","cited_by_count":24},{"id":"1512.01563","title":"State of the Art Control of Atari Games Using Shallow Reinforcement Learning","created":"2015-12-04","cited_by_count":23},{"id":"1804.07726","title":"Phrase-Indexed Question Answering: A New Challenge for Scalable Document Comprehension","created":"2018-04-20","cited_by_count":23},{"id":"1905.10360","title":"The advantages of multiple classes for reducing overfitting from test set reuse","created":"2019-05-24","cited_by_count":14},{"id":"2102.12887","title":"Significant Improvements over the State of the Art? A Case Study of the MS MARCO Document Ranking Leaderboard","created":"2021-02-25","cited_by_count":12},{"id":"1908.10396","title":"Accelerating Large-Scale Inference with Anisotropic Vector Quantization","created":"2019-08-27","cited_by_count":9},{"id":"2102.13189","title":"Rip van Winkle's Razor: A Simple Estimate of Overfit to Test Data","created":"2021-02-25","cited_by_count":8},{"id":"1805.07037","title":"MARS: Memory Attention-Aware Recommender System","created":"2018-05-18","cited_by_count":1}],"next_cursor":null}