{"list":"other","total":59,"rows":[{"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":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"id":"1312.6114","title":"Auto-Encoding Variational Bayes","created":"2013-12-20","cited_by_count":4053},{"id":"1703.05175","title":"Prototypical Networks for Few-shot Learning","created":"2017-03-15","cited_by_count":3015},{"id":"1505.05770","title":"Variational Inference with Normalizing Flows","created":"2015-05-21","cited_by_count":2170},{"id":"1506.02438","title":"High-Dimensional Continuous Control Using Generalized Advantage Estimation","created":"2015-06-08","cited_by_count":2026},{"id":"1911.08731","title":"Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization","created":"2019-11-20","cited_by_count":1247},{"id":"1910.10897","title":"Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning","created":"2019-10-24","cited_by_count":1204},{"id":"1609.09106","title":"HyperNetworks","created":"2016-09-27","cited_by_count":1027},{"id":"2101.01169","title":"Transformers in Vision: A Survey","created":"2021-01-04","cited_by_count":1013},{"id":"2004.05439","title":"Meta-Learning in Neural Networks: A Survey","created":"2020-04-11","cited_by_count":950},{"id":"1611.01236","title":"Adversarial Machine Learning at Scale","created":"2016-11-04","cited_by_count":936},{"id":"1909.04630","title":"Meta-Learning with Implicit Gradients","created":"2019-09-10","cited_by_count":525},{"id":"1611.02779","title":"RL$^2$: Fast Reinforcement Learning via Slow Reinforcement Learning","created":"2016-11-09","cited_by_count":503},{"id":"1807.05960","title":"Meta-Learning with Latent Embedding Optimization","created":"2018-07-16","cited_by_count":476},{"id":"2111.01243","title":"Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Survey","created":"2021-11-01","cited_by_count":463},{"id":"2007.00644","title":"Measuring Robustness to Natural Distribution Shifts in Image Classification","created":"2020-07-01","cited_by_count":454},{"id":"1807.01613","title":"Conditional Neural Processes","created":"2018-07-04","cited_by_count":426},{"id":"1807.01622","title":"Neural Processes","created":"2018-07-04","cited_by_count":311},{"id":"1901.05761","title":"Attentive Neural Processes","created":"2019-01-17","cited_by_count":283},{"id":"2012.02096","title":"Emergent Complexity and Zero-shot Transfer via Unsupervised Environment Design","created":"2020-12-03","cited_by_count":275},{"id":"1703.00837","title":"Meta Networks","created":"2017-03-02","cited_by_count":269},{"id":"2109.04617","title":"Efficiently Identifying Task Groupings for Multi-Task Learning","created":"2021-09-10","cited_by_count":222},{"id":"2312.00785","title":"Sequential Modeling Enables Scalable Learning for Large Vision Models","created":"2023-12-01","cited_by_count":212},{"id":"2007.02931","title":"Adaptive Risk Minimization: Learning to Adapt to Domain Shift","created":"2020-07-06","cited_by_count":183},{"id":"2203.01302","title":"Evolving Curricula with Regret-Based Environment Design","created":"2022-03-02","cited_by_count":173},{"id":"1904.04762","title":"Active Domain Randomization","created":"2019-04-09","cited_by_count":170},{"id":"1910.13556","title":"Convolutional Conditional Neural Processes","created":"2019-10-29","cited_by_count":142},{"id":"2112.05077","title":"Generating Useful Accident-Prone Driving Scenarios via a Learned Traffic Prior","created":"2021-12-09","cited_by_count":139},{"id":"1908.10400","title":"On the Convergence Theory of Gradient-Based Model-Agnostic Meta-Learning Algorithms","created":"2019-08-27","cited_by_count":132},{"id":"1906.07697","title":"Fast and Flexible Multi-Task Classification Using Conditional Neural Adaptive Processes","created":"2019-06-18","cited_by_count":131},{"id":"1902.04552","title":"Infinite Mixture Prototypes for Few-Shot Learning","created":"2019-02-12","cited_by_count":99},{"id":"2005.06800","title":"Context-aware Dynamics Model for Generalization in Model-Based Reinforcement Learning","created":"2020-05-14","cited_by_count":98},{"id":"2101.06541","title":"SceneGen: Learning to Generate Realistic Traffic Scenes","created":"2021-01-16","cited_by_count":84},{"id":"2103.15402","title":"Mining Latent Classes for Few-shot Segmentation","created":"2021-03-29","cited_by_count":69},{"id":"2106.04252","title":"Meta-Learning to Compositionally Generalize","created":"2021-06-08","cited_by_count":62},{"id":"2007.05549","title":"Meta-Learning Requires Meta-Augmentation","created":"2020-07-10","cited_by_count":57},{"id":"2007.13040","title":"Improving Generalization in Meta-learning via Task Augmentation","created":"2020-07-26","cited_by_count":55},{"id":"2008.06622","title":"Cautious Adaptation For Reinforcement Learning in Safety-Critical Settings","created":"2020-08-15","cited_by_count":42},{"id":"2010.07092","title":"Data Augmentation for Meta-Learning","created":"2020-10-14","cited_by_count":38},{"id":"2104.01678","title":"Understanding Continual Learning Settings with Data Distribution Drift Analysis","created":"2021-04-04","cited_by_count":38},{"id":"2008.09469","title":"Doubly Stochastic Variational Inference for Neural Processes with Hierarchical Latent Variables","created":"2020-08-21","cited_by_count":33},{"id":"2102.04002","title":"Meta Discovery: Learning to Discover Novel Classes given Very Limited Data","created":"2021-02-08","cited_by_count":31},{"id":"2007.08735","title":"Adaptive Task Sampling for Meta-Learning","created":"2020-07-17","cited_by_count":29},{"id":"2110.14057","title":"Meta-learning with an Adaptive Task Scheduler","created":"2021-10-26","cited_by_count":27},{"id":"2202.08045","title":"Learning to Generalize across Domains on Single Test Samples","created":"2022-02-16","cited_by_count":24},{"id":"2402.10099","title":"Any-Shift Prompting for Generalization over Distributions","created":"2024-02-15","cited_by_count":24},{"id":"2006.13182","title":"On the Global Optimality of Model-Agnostic Meta-Learning","created":"2020-06-23","cited_by_count":21},{"id":"1902.00618","title":"What is Local Optimality in Nonconvex-Nonconcave Minimax Optimization?","created":"2019-02-02","cited_by_count":20},{"id":"2106.06326","title":"TOHAN: A One-step Approach towards Few-shot Hypothesis Adaptation","created":"2021-06-11","cited_by_count":17},{"id":"2302.11215","title":"Energy-Based Test Sample Adaptation for Domain Generalization","created":"2023-02-22","cited_by_count":14},{"id":"2310.00708","title":"A Simple Yet Effective Strategy to Robustify the Meta Learning Paradigm","created":"2023-10-01","cited_by_count":10},{"id":"1802.05193","title":"Security Analysis and Enhancement of Model Compressed Deep Learning Systems under Adversarial Attacks","created":"2018-02-14","cited_by_count":8},{"id":"2310.18713","title":"Episodic Multi-Task Learning with Heterogeneous Neural Processes","created":"2023-10-28","cited_by_count":8},{"id":"2205.09990","title":"Set-based Meta-Interpolation for Few-Task Meta-Learning","created":"2022-05-20","cited_by_count":7},{"id":"1910.00982","title":"Adversarially Robust Few-Shot Learning: A Meta-Learning Approach","created":"2019-10-02","cited_by_count":6},{"id":"2308.02561","title":"Large-scale Generative Simulation Artificial Intelligence: the Next Hotspot in Generative AI","created":"2023-08-03","cited_by_count":5},{"id":"1911.06968","title":"Defensive Few-shot Learning","created":"2019-11-16","cited_by_count":3}],"next_cursor":null}