{"list":"other","total":84,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"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":"1506.02142","title":"Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning","created":"2015-06-06","cited_by_count":4448},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"1612.01474","title":"Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles","created":"2016-12-05","cited_by_count":3926},{"id":"1701.06538","title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer","created":"2017-01-23","cited_by_count":3509},{"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":"1903.12261","title":"Benchmarking Neural Network Robustness to Common Corruptions and Perturbations","created":"2019-03-28","cited_by_count":2877},{"id":"1704.05426","title":"A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference","created":"2017-04-18","cited_by_count":2682},{"id":"1610.02136","title":"A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks","created":"2016-10-07","cited_by_count":2385},{"id":"1703.04977","title":"What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?","created":"2017-03-15","cited_by_count":2352},{"id":"1311.3618","title":"Describing Textures in the Wild","created":"2013-11-14","cited_by_count":2125},{"id":"1308.3432","title":"Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation","created":"2013-08-15","cited_by_count":2079},{"id":"2206.04615","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","created":"2022-06-09","cited_by_count":1998},{"id":"2004.07780","title":"Shortcut Learning in Deep Neural Networks","created":"2020-04-16","cited_by_count":1969},{"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":"1606.06565","title":"Concrete Problems in AI Safety","created":"2016-06-21","cited_by_count":1642},{"id":"2006.16668","title":"GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding","created":"2020-06-30","cited_by_count":1631},{"id":"1902.10811","title":"Do ImageNet Classifiers Generalize to ImageNet?","created":"2019-02-13","cited_by_count":1515},{"id":"1807.03888","title":"A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks","created":"2018-07-10","cited_by_count":1485},{"id":"1907.07174","title":"Natural Adversarial Examples","created":"2019-07-16","cited_by_count":1408},{"id":"1906.02530","title":"Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift","created":"2019-06-06","cited_by_count":1287},{"id":"2201.08239","title":"LaMDA: Language Models for Dialog Applications","created":"2022-01-20","cited_by_count":1220},{"id":"2106.04560","title":"Scaling Vision Transformers","created":"2021-06-08","cited_by_count":999},{"id":"1902.01007","title":"Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inference","created":"2019-02-04","cited_by_count":876},{"id":"1703.02910","title":"Deep Bayesian Active Learning with Image Data","created":"2017-03-08","cited_by_count":819},{"id":"1912.11370","title":"Big Transfer (BiT): General Visual Representation Learning","created":"2019-12-24","cited_by_count":769},{"id":"2106.05974","title":"Scaling Vision with Sparse Mixture of Experts","created":"2021-06-10","cited_by_count":747},{"id":"1505.05424","title":"Weight Uncertainty in Neural Networks","created":"2015-05-20","cited_by_count":554},{"id":"1906.12340","title":"Using Self-Supervised Learning Can Improve Model Robustness and Uncertainty","created":"2019-06-28","cited_by_count":514},{"id":"2011.03395","title":"Underspecification Presents Challenges for Credibility in Modern Machine Learning","created":"2020-11-06","cited_by_count":496},{"id":"1911.11132","title":"Scaling Out-of-Distribution Detection for Real-World Settings","created":"2019-11-25","cited_by_count":465},{"id":"2007.00644","title":"Measuring Robustness to Natural Distribution Shifts in Image Classification","created":"2020-07-01","cited_by_count":454},{"id":"1904.01685","title":"Measuring Calibration in Deep Learning","created":"2019-04-02","cited_by_count":446},{"id":"1903.04561","title":"Nuanced Metrics for Measuring Unintended Bias with Real Data for Text Classification","created":"2019-03-11","cited_by_count":404},{"id":"2106.07998","title":"Revisiting the Calibration of Modern Neural Networks","created":"2021-06-15","cited_by_count":390},{"id":"2006.10108","title":"Simple and Principled Uncertainty Estimation with Deterministic Deep Learning via Distance Awareness","created":"2020-06-17","cited_by_count":389},{"id":"1909.02027","title":"An Evaluation Dataset for Intent Classification and Out-of-Scope Prediction","created":"2019-09-04","cited_by_count":386},{"id":"1901.09960","title":"Using Pre-Training Can Improve Model Robustness and Uncertainty","created":"2019-01-28","cited_by_count":373},{"id":"2002.06715","title":"BatchEnsemble: An Alternative Approach to Efficient Ensemble and Lifelong Learning","created":"2020-02-17","cited_by_count":371},{"id":"2006.07159","title":"Are we done with ImageNet?","created":"2020-06-12","cited_by_count":333},{"id":"1811.08581","title":"Recent Advances in Open Set Recognition: A Survey","created":"2018-11-21","cited_by_count":310},{"id":"2109.13916","title":"Unsolved Problems in ML Safety","created":"2021-09-28","cited_by_count":292},{"id":"2106.03004","title":"Exploring the Limits of Out-of-Distribution Detection","created":"2021-06-06","cited_by_count":283},{"id":"1908.07086","title":"Human uncertainty makes classification more robust","created":"2019-08-19","cited_by_count":235},{"id":"1610.08914","title":"Ex Machina: Personal Attacks Seen at Scale","created":"2016-10-27","cited_by_count":210},{"id":"2106.09022","title":"A Simple Fix to Mahalanobis Distance for Improving Near-OOD Detection","created":"2021-06-16","cited_by_count":207},{"id":"1906.01620","title":"Evaluating Scalable Bayesian Deep Learning Methods for Robust Computer Vision","created":"2019-06-04","cited_by_count":182},{"id":"2111.10050","title":"Combined Scaling for Zero-shot Transfer Learning","created":"2021-11-19","cited_by_count":182},{"id":"2005.07186","title":"Efficient and Scalable Bayesian Neural Nets with Rank-1 Factors","created":"2020-05-14","cited_by_count":171},{"id":"1511.06297","title":"Conditional Computation in Neural Networks for faster models","created":"2015-11-19","cited_by_count":167},{"id":"1903.05566","title":"Benchmarking Natural Language Understanding Services for building Conversational Agents","created":"2019-03-13","cited_by_count":166},{"id":"2008.04859","title":"BREEDS: Benchmarks for Subpopulation Shift","created":"2020-08-11","cited_by_count":155},{"id":"2007.06778","title":"An Empirical Study on Robustness to Spurious Correlations using Pre-trained Language Models","created":"2020-07-14","cited_by_count":134},{"id":"2012.07923","title":"Improving model calibration with accuracy versus uncertainty optimization","created":"2020-12-14","cited_by_count":123},{"id":"1808.05697","title":"Deep Bayesian Active Learning for Natural Language Processing: Results of a Large-Scale Empirical Study","created":"2018-08-16","cited_by_count":90},{"id":"2201.03529","title":"Head2Toe: Utilizing Intermediate Representations for Better Transfer Learning","created":"2022-01-10","cited_by_count":83},{"id":"2106.04015","title":"Uncertainty Baselines: Benchmarks for Uncertainty & Robustness in Deep Learning","created":"2021-06-07","cited_by_count":82},{"id":"1602.03506","title":"Research Priorities for Robust and Beneficial Artificial Intelligence","created":"2016-02-10","cited_by_count":74},{"id":"2110.14216","title":"What Do We Mean by Generalization in Federated Learning?","created":"2021-10-27","cited_by_count":62},{"id":"1906.02168","title":"Do Image Classifiers Generalize Across Time?","created":"2019-06-05","cited_by_count":59},{"id":"1904.11643","title":"Bayesian Generative Active Deep Learning","created":"2019-04-26","cited_by_count":57},{"id":"2205.00403","title":"A Simple Approach to Improve Single-Model Deep Uncertainty via Distance-Awareness","created":"2022-05-01","cited_by_count":49},{"id":"2010.09875","title":"Combining Ensembles and Data Augmentation can Harm your Calibration","created":"2020-10-19","cited_by_count":44},{"id":"1906.03842","title":"Analyzing the Role of Model Uncertainty for Electronic Health Records","created":"2019-06-10","cited_by_count":41},{"id":"1907.00865","title":"Radial Bayesian Neural Networks: Beyond Discrete Support In Large-Scale Bayesian Deep Learning","created":"2019-07-01","cited_by_count":37},{"id":"2105.10305","title":"Correlated Input-Dependent Label Noise in Large-Scale Image Classification","created":"2021-05-19","cited_by_count":37},{"id":"2204.08491","title":"Active Learning Helps Pretrained Models Learn the Intended Task","created":"2022-04-18","cited_by_count":33},{"id":"1803.00967","title":"Active model learning and diverse action sampling for task and motion planning","created":"2018-03-02","cited_by_count":28},{"id":"1805.01109","title":"AGI Safety Literature Review","created":"2018-05-03","cited_by_count":28},{"id":"2111.12880","title":"Active Learning at the ImageNet Scale","created":"2021-11-25","cited_by_count":28},{"id":"1802.07427","title":"Active Learning with Partial Feedback","created":"2018-02-21","cited_by_count":27},{"id":"2201.07459","title":"PT4AL: Using Self-Supervised Pretext Tasks for Active Learning","created":"2022-01-19","cited_by_count":27},{"id":"2106.04564","title":"Are Pretrained Transformers Robust in Intent Classification? A Missing Ingredient in Evaluation of Out-of-Scope Intent Detection","created":"2021-06-08","cited_by_count":22},{"id":"2110.03360","title":"Sparse MoEs meet Efficient Ensembles","created":"2021-10-07","cited_by_count":19},{"id":"1811.02091","title":"Simple, Distributed, and Accelerated Probabilistic Programming","created":"2018-11-05","cited_by_count":18},{"id":"2107.04212","title":"Measuring and Improving Model-Moderator Collaboration using Uncertainty Estimation","created":"2021-07-09","cited_by_count":18},{"id":"1912.00594","title":"Combining MixMatch and Active Learning for Better Accuracy with Fewer Labels","created":"2019-12-02","cited_by_count":17},{"id":"2109.02008","title":"Cross-token Modeling with Conditional Computation","created":"2021-09-05","cited_by_count":17},{"id":"2112.07773","title":"Filling gaps in trustworthy development of AI","created":"2021-12-14","cited_by_count":14}],"next_cursor":null}