{"list":"other","total":51,"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":"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":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019},{"id":"1703.05175","title":"Prototypical Networks for Few-shot Learning","created":"2017-03-15","cited_by_count":3015},{"id":"2106.01946","title":"Convex optimization","created":"2021-06-03","cited_by_count":2515},{"id":"1606.04080","title":"Matching Networks for One Shot Learning","created":"2016-06-13","cited_by_count":2255},{"id":"1907.07174","title":"Natural Adversarial Examples","created":"2019-07-16","cited_by_count":1408},{"id":"2012.15723","title":"Making Pre-trained Language Models Better Few-shot Learners","created":"2020-12-31","cited_by_count":1256},{"id":"1905.13549","title":"Learning Robust Global Representations by Penalizing Local Predictive Power","created":"2019-05-29","cited_by_count":1013},{"id":"2004.05439","title":"Meta-Learning in Neural Networks: A Survey","created":"2020-04-11","cited_by_count":950},{"id":"2210.03117","title":"MaPLe: Multi-modal Prompt Learning","created":"2022-10-06","cited_by_count":687},{"id":"2104.10350","title":"Carbon Emissions and Large Neural Network Training","created":"2021-04-21","cited_by_count":567},{"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":"1904.03758","title":"Meta-Learning with Differentiable Convex Optimization","created":"2019-04-07","cited_by_count":461},{"id":"1803.00676","title":"Meta-Learning for Semi-Supervised Few-Shot Classification","created":"2018-03-02","cited_by_count":456},{"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":"1911.02590","title":"Optimizing Millions of Hyperparameters by Implicit Differentiation","created":"2019-11-06","cited_by_count":304},{"id":"2102.01293","title":"Scaling Laws for Transfer","created":"2021-02-02","cited_by_count":272},{"id":"1906.00331","title":"On Gradient Descent Ascent for Nonconvex-Concave Minimax Problems","created":"2019-06-02","cited_by_count":270},{"id":"1806.02817","title":"Probabilistic Model-Agnostic Meta-Learning","created":"2018-06-07","cited_by_count":256},{"id":"1801.08930","title":"Recasting Gradient-Based Meta-Learning as Hierarchical Bayes","created":"2018-01-26","cited_by_count":180},{"id":"2304.01852","title":"Summary of ChatGPT-Related Research and Perspective Towards the Future of Large Language Models","created":"2023-04-04","cited_by_count":154},{"id":"2101.11517","title":"Investigating Bi-Level Optimization for Learning and Vision from a Unified Perspective: A Survey and Beyond","created":"2021-01-27","cited_by_count":153},{"id":"1805.09921","title":"Meta-Learning Probabilistic Inference For Prediction","created":"2018-05-24","cited_by_count":110},{"id":"1902.04552","title":"Infinite Mixture Prototypes for Few-Shot Learning","created":"2019-02-12","cited_by_count":99},{"id":"2007.01332","title":"Meta-Learning Stationary Stochastic Process Prediction with Convolutional Neural Processes","created":"2020-07-02","cited_by_count":76},{"id":"2110.07356","title":"Medically Aware GPT-3 as a Data Generator for Medical Dialogue Summarization","created":"2021-09-09","cited_by_count":76},{"id":"2309.14393","title":"LLMCarbon: Modeling the end-to-end Carbon Footprint of Large Language Models","created":"2023-09-25","cited_by_count":72},{"id":"1902.03356","title":"Meta-Curvature","created":"2019-02-09","cited_by_count":70},{"id":"2206.03996","title":"Sharp-MAML: Sharpness-Aware Model-Agnostic Meta Learning","created":"2022-06-08","cited_by_count":58},{"id":"1903.10399","title":"Learning-to-Learn Stochastic Gradient Descent with Biased Regularization","created":"2019-03-25","cited_by_count":49},{"id":"2109.14595","title":"Generalization Bounds For Meta-Learning: An Information-Theoretic Analysis","created":"2021-09-29","cited_by_count":45},{"id":"2210.11348","title":"Hypernetworks in Meta-Reinforcement Learning","created":"2022-10-20","cited_by_count":42},{"id":"2008.02956","title":"Bootstrapping Neural Processes","created":"2020-08-07","cited_by_count":40},{"id":"2309.12696","title":"Counterfactual Conservative Q Learning for Offline Multi-agent Reinforcement Learning","created":"2023-09-22","cited_by_count":37},{"id":"2008.09469","title":"Doubly Stochastic Variational Inference for Neural Processes with Hierarchical Latent Variables","created":"2020-08-21","cited_by_count":33},{"id":"2010.05843","title":"How Important is the Train-Validation Split in Meta-Learning?","created":"2020-10-12","cited_by_count":30},{"id":"2102.10454","title":"On Fast Adversarial Robustness Adaptation in Model-Agnostic Meta-Learning","created":"2021-02-20","cited_by_count":29},{"id":"2311.08935","title":"Supported Trust Region Optimization for Offline Reinforcement Learning","created":"2023-11-15","cited_by_count":20},{"id":"2010.07093","title":"Function Contrastive Learning of Transferable Meta-Representations","created":"2020-10-14","cited_by_count":19},{"id":"2102.08291","title":"Model-based Meta Reinforcement Learning using Graph Structured Surrogate Models","created":"2021-02-16","cited_by_count":17},{"id":"2407.19523","title":"Robust Fast Adaptation from Adversarially Explicit Task Distribution Generation","created":"2024-07-28","cited_by_count":13},{"id":"2408.10556","title":"Hokoff: Real Game Dataset from Honor of Kings and its Offline Reinforcement Learning Benchmarks","created":"2024-08-20","cited_by_count":11},{"id":"2310.00708","title":"A Simple Yet Effective Strategy to Robustify the Meta Learning Paradigm","created":"2023-10-01","cited_by_count":10},{"id":"2210.15551","title":"Terminology-aware Medical Dialogue Generation","created":"2022-10-27","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":"2308.02561","title":"Large-scale Generative Simulation Artificial Intelligence: the Next Hotspot in Generative AI","created":"2023-08-03","cited_by_count":5}],"next_cursor":null}