{"total":21,"rows":[{"id":"2505.24760","title":"REASONING GYM: Reasoning Environments for Reinforcement Learning with Verifiable Rewards","created":"2025-05-30","cited_by_count":130,"area":null},{"id":"2202.00661","title":"When Do Flat Minima Optimizers Work?","created":"2022-02-01","cited_by_count":78,"area":null},{"id":"2304.08442","title":"The MiniPile Challenge for Data-Efficient Language Models","created":"2023-04-17","cited_by_count":75,"area":null},{"id":"2202.03091","title":"Auto-Lambda: Disentangling Dynamic Task Relationships","created":"2022-02-07","cited_by_count":73,"area":null},{"id":"2303.05470","title":"Spawrious: A Benchmark for Fine Control of Spurious Correlation Biases","created":"2023-03-09","cited_by_count":41,"area":null},{"id":"2110.14057","title":"Meta-learning with an Adaptive Task Scheduler","created":"2021-10-26","cited_by_count":27,"area":null},{"id":"2103.03697","title":"Bayesian Meta-Learning for Few-Shot Policy Adaptation Across Robotic Platforms","created":"2021-03-05","cited_by_count":22,"area":null},{"id":"2110.02102","title":"CARL: A Benchmark for Contextual and Adaptive Reinforcement Learning","created":"2021-10-05","cited_by_count":21,"area":null},{"id":"2501.11039","title":"Model Predictive Task Sampling for Efficient and Robust Adaptation","created":"2025-01-19","cited_by_count":21,"area":null},{"id":"2105.13524","title":"Improving Generalization in Meta-RL with Imaginary Tasks from Latent Dynamics Mixture","created":"2021-05-28","cited_by_count":12,"area":null},{"id":"2203.12768","title":"Multidimensional Belief Quantification for Label-Efficient Meta-Learning","created":"2022-03-23","cited_by_count":9,"area":null},{"id":"2211.05980","title":"Hardness-guided domain adaptation to recognise biomedical named entities under low-resource scenarios","created":"2022-11-11","cited_by_count":6,"area":null},{"id":"2106.04802","title":"Probabilistic task modelling for meta-learning","created":"2021-06-09","cited_by_count":4,"area":null},{"id":"2108.00785","title":"Bayesian Active Meta-Learning for Few Pilot Demodulation and Equalization","created":"2021-08-02","cited_by_count":2,"area":null},{"id":"2402.15441","title":"Active Few-Shot Fine-Tuning","created":"2024-02-13","cited_by_count":2,"area":null},{"id":"2402.16105","title":"Towards Automated Knowledge Integration From Human-Interpretable Representations","created":"2024-02-25","cited_by_count":2,"area":null},{"id":"2405.07083","title":"Data-Efficient and Robust Task Selection for Meta-Learning","created":"2024-05-11","cited_by_count":2,"area":null},{"id":"2311.02879","title":"Exploring Active Learning in Meta-Learning: Enhancing Context Set Labeling","created":"2023-11-06","cited_by_count":1,"area":null},{"id":"2107.10763","title":"Learning to Transfer: A Foliated Theory","created":"2021-07-22","cited_by_count":0,"area":null},{"id":"2210.06891","title":"Experimental Design for Multi-Channel Imaging via Task-Driven Feature Selection","created":"2022-10-13","cited_by_count":0,"area":null},{"id":"2602.17605","title":"Adapting Actively on the Fly: Relevance-Guided Online Meta-Learning with Latent Concepts for Geospatial Discovery","created":"2026-02-19","cited_by_count":0,"area":null}],"next_cursor":null}