Meta-Learning

Ask about this topic

Overview

Meta-learning studies how experience across related tasks can prepare a model to learn a new task from a small support set, brief feedback, or context alone. Common approaches include gradient-based initialization methods such as MAML, metric and prototype methods, Bayesian methods, learned optimizers and hypernetworks, and episodic training for in-context or test-time adaptation. Applications range from few-shot vision and domain-shifted control to AutoML, scientific system identification, and language or robotic agents, where fast adaptation can reduce labeling, retraining, or optimization costs. The central challenge is transferring useful shared structure without negative transfer: task diversity, distribution shift, uncertainty, costly bilevel training, and fair evaluation of adaptation remain active concerns.

Latest papers

CardsList

166 papers20 papers in the last four weeks, level with the four weeks before. 0.1% of all new papers.

  1. Bigger Is Safer: Provable Robustness in In-Context Learning Scales with Capacity

    Feb 19, 2026Di Zhang, Ningxu Zhang, Zimeng LiuIn-Context LearningDistribution Shift Robustness

    School of AI and Advanced Computing Xi’an Jiaotong-Liverpool University

  2. Learning to Learn from Language Feedback with Social Meta-Learning

    Feb 18, 2026Jonathan Cook, Diego Antognini, Martin Klissarov +2Meta-LearningLLM Fine-Tuning

    Google DeepMind

  3. Universal Algorithm-Implicit Learning

    Feb 16, 2026Stefano Woerner, Seong Joon Oh, Christian F. BaumgartnerMeta-LearningFew-Shot Learning

    University of Tübingen, Germany · KAIST, Korea · Faculty of Health Sciences and Medicine, University of Lucerne, Switzerland

  4. Trust Region Continual Learning as an Implicit Meta-Learner

    Feb 2, 2026Zekun Wang, Anant Gupta, Christopher J. MacLellanReplay-Based Continual LearningTask-Incremental Learning

    Georgia Institute of Technology

  5. DUPLE: An Intelligent Cross-Deployment Recognition Framework for Fiber-Optic Perimeter Security under Scarce Target Labels

    Nov 22, 2025Yifan He, Haodong Zhang, Qiuheng Song +4Distribution Shift RobustnessMeta-Learning

    College of Smart Materials and Future Energy, Fiber-Optic Research Center, Fudan University, Shanghai 200433, China · School of Software, Northwestern Polytechnical University, Xi’an 710129, China · Sichuan Fujinan Technology Co., Ltd., Chengdu 611400, China +1

  6. Towards Scalable Meta-Learning of near-optimal Interpretable Models via Synthetic Model Generations

    Nov 6, 2025Kyaw Hpone Myint, Zhe Wu, Alexandre G. R. Day +1Decision Tree LearningMeta-Learning

    Capital One

  7. MetaCaDI: A Meta-Learning Framework for Causal Discovery from Multiple Environments with Unknown Interventions

    Oct 25, 2025Hans Jarett Ong, Yoichi Chikahara, Tomoharu IwataMeta-LearningCausal Discovery

    Nara Institute of Science and Technology, Nara, Japan · NTT Communication Science Laboratories, Kyoto, Japan

  8. Metadata-Guided Adaptable Frequency Scaling across Heterogeneous Applications and Devices

    Sep 23, 2025Jinqi Yan, Fang He, Qianlong Sang +5Meta-LearningMulti-Task RL

    School of Computer Science, Wuhan University · School of Computer Science and Artificial Intelligence, Wuhan University of Technology · OPPO Guangdong Mobile Communications Co., Ltd.

  9. Effects of Structural Allocation of Geometric Task Diversity in Linear Meta-Learning Models

    Sep 22, 2025Saptati Datta, Nicolas W. Hengartner, Yulia Pimonova +2Meta-LearningFew-Shot Learning

    Department of Statistics, Texas A&M University, TX, USA · Los Alamos National Laboratory, Los Alamos, USA.

  10. Meta-learning ecological priors from large language models explains human learning and decision making

    Aug 28, 2025Akshay K. Jagadish, Mirko Thalmann, Julian Coda-Forno +2Computational Cognitive ModelingMeta-Learning

    Institute for Human-Centered AI, Helmholtz Computational Health Center, Munich, Germany · Computational Principles of Intelligence, Max Planck Institute for Biological Cybernetics, Tübingen, Germany · Eberhard Karls University of Tübingen, Tübingen, Germany +1

  11. Meta-learning of Gibbs states for many-body Hamiltonians with applications to Quantum Boltzmann Machines

    Jul 22, 2025Ruchira V Bhat, Rahul Bhowmick, Avinash Singh +1Quantum State PreparationMeta-Learning

    Quantum Lab, Fujitsu Research of India

  12. Manifold meta-learning for reduced-complexity neural system identification

    Apr 16, 2025Marco Forgione, Ankush Chakrabarty, Dario Piga +2System IdentificationMeta-Learning

    SUPSI, IDSIA - Dalle Molle Institute for Artificial Intelligence, Lugano, Switzerland. · Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA. · IMT School for Advanced Studies Lucca, Lucca, Italy.

  13. DRESS: Disentangled Representation-based Self-Supervised Meta-Learning for Diverse Tasks

    Mar 12, 2025Wei Cui, Tongzi Wu, Jesse C. Cresswell +2Disentangled Representation LearningMeta-Learning

    Layer 6 AI, Toronto, Canada

  14. Pairwise Difference Learning for Classification

    Jun 28, 2024Mohamed Karim Belaid, Maximilian Rabus, Eyke HüllermeierClassificationMeta-Learning

    IDIADA Fahrzeugtechnik GmbH, Munich, Germany · Dr. Ing. h.c. F. Porsche AG Stuttgart, Germany · Ludwig-Maximilians-Universität Munich, Germany

  15. From system models to class models: An in-context learning paradigm

    Aug 25, 2023Marco Forgione, Filippo Pura, Dario PigaMeta-LearningIn-Context Learning

    IDSIA Dalle Molle Institute for Artificial Intelligence USI-SUPSI, Via la Santa 1, CH-6962 Lugano-Viganello, Switzerland.

  16. Ensemble Learning Based Classification Algorithm Recommendation

    Jan 15, 2021Guangtao Wang, Qinbao Song, Xiaoyan Zhu +1Algorithm SelectionEnsemble Learning

    Department of Computer Science and Technology, Xi’an Jiaotong University, China