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. Meta Models: Models that Model Learning

    Oct 27, 2026Peihang Li, Ziming LiuLanguage Model Performance PredictionMeta-Learning

    MetaCircle · The University of Hong Kong · University of California, Berkeley +2

  2. MetaARIMA: Configuration-Level Transfer Learning for ARIMA Models

    Oct 25, 2026Vitor Cerqueira, Ricardo Inácio, Carlos SoaresTime Series ModelingTime Series Forecasting

    University of Coimbra; CISUC/LASI – Centre for Informatics and Systems of the University of Coimbra; Coimbra, Portugal · Faculty of Engineering, University of Porto; Porto, Portugal · Faculty of Engineering, University of Porto; Laboratory for Artificial Intelligence and Computer Science (LIACC), Portugal; Fraunhofer Portugal AICOS, Portugal; Porto, Portugal

  3. SyRA-CS: Synthetic-to-Real Adaptation for Code-Switched ASR with Meta-Learning

    Oct 22, 2026Fadel Thior, Ahmer Tabassum, Haania Siddiqui +2Code-Switching Speech RecognitionSynthetic-to-Real Domain Adaptation

    Mohamed bin Zayed University of Artificially Intelligence

  4. MuPACE: Learning to Pace Muon for LoRA Fine-Tuning

    Oct 20, 2026Jan Kobiolka, Christian Frey, Josif GrabockaLearning Rate SchedulingAdaptive Learning Rate

    Department of Computer Science, University of Technology Nuremberg, Nuremberg, Germany

  5. Meta-iLaD: Identifiable Latent Dynamics via Meta-Learning of Dynamics Environments

    Oct 19, 2026Yubo Ye, Sweekar Piya, Xiajun Jiang +1Latent Dynamics ModelingTime Series Forecasting

    Department of Computing and Information Sciences, Rochester Institute of Technology, Rochester, New York, USA · Department of Computer Science, Rowan University, Glassboro, New Jersey, USA

  6. Cognitively Decoupled Meta-Induction for Out-of-Distribution Generalization

    Oct 19, 2026Yuqian Wang, Yuanzheng Wang, Chaojun Xiao +7Inductive Reasoning in Language ModelsOOD Generalization

    Beijing Institute of Technology · University of Chinese Academy of Sciences · Department of Computer Science and Technology, Tsinghua University +4

  7. LUMINR: Intensity-conditioned Meta-learned INRs for Accelerated Medical Image Registration

    Oct 16, 2026Damian Rynczak, Marek WodzinskiMedical Image RegistrationDeformable Image Registration

    AGH University of Krakow · Sano - Centre for Computational Personalised Medicine, International Research Foundation

  8. Active Generative Simulation: Meta-Learning What to Simulate for Sim-and-Real Policy Co-Training

    Oct 14, 2026Liqian Ma, Vaibhav Saxena, Utkarsh Aashu Mishra +3Synthetic Data Generation for RoboticsSim-to-Real Transfer

    Georgia Institute of Technology

  9. MetaOPD: Meta-Learned Token Weighting for On-Policy Distillation

    Oct 8, 2026Zipeng Wang, Xinpeng Dong, Yuefan Wang +6On-Policy DistillationAdaptive Loss Weighting

    East China Normal University · Zhejiang University · The Chinese University of Hong Kong, Shenzhen

  10. MotherTree: Meta-learning on synthetic data improves decision tree training

    Oct 7, 2026Ziyuan Wang, Fredrik D. JohanssonDecision Tree LearningMeta-Learning

    Chalmers University of Technology University of Gothenburg

  11. MetaLearnNCA: Few-Shot Offline Meta-Learning via Interacting Neural Cellular Automata

    Oct 6, 2026Etienne Guichard, Stefano NicheleNeural Cellular AutomataMeta-Learning

    Department of Computer Science and Communication hiof.no

  12. Learning PDE solution operators with variable initial conditions via Latent Dynamics Networks

    Oct 6, 2026Stefano Maria Pizzamiglio, Stefano Pagani, Francesco RegazzoniLatent Dynamics ModelingMeta-Learning

    MOX Laboratory, Department of Mathematics, Politecnico di Milano, Italy

  13. Optimization Encoders: Rethinking Second-Order Meta-Learning for Neural Fields

    Oct 6, 2026Rudolf L. M. van Herten, Soufiane Ben Haddou, Rachit Saluja +1Implicit Neural RepresentationsMeta-Learning

    Weill Cornell Medicine · Cornell Tech · Amsterdam UMC

  14. Few-Shot Bioactivity Prediction with Meta-Learning under Assay Heterogeneity

    Oct 5, 2026Michal Kmicikiewicz, Tommy Rochussen, Vincent Fortuin +1Meta-LearningFew-Shot Learning

    Institute of AI for Health, Helmholtz Munich · School of Computation, Information and Technology, Technical University of Munich · Munich Center for Machine Learning +4

  15. Learning to Learn a Language

    Oct 5, 2026Lennart Carstens-Behrens, Holger FröhlichLanguage Model PretrainingMeta-Learning

    Fraunhofer Institute for Algorithms and Scientific Computing SCAI · University Hospital Bonn

  16. RepICL: Reusable In-Context Prediction Across Heterogeneous Representation Spaces

    Oct 5, 2026Yu-Hsiang Liu, Kuan-Yu Chen, Chih-Sheng Chen +3Meta-LearningFew-Shot Learning

    SinoPac Holdings, Taipei, Taiwan

  17. TMAML: Temporal Model-Agnostic Meta-Learning for Cold-Start Time Series Forecasting

    Oct 3, 2026Wannes Janssens, Matthias Bogaert, Dirk Van den PoelTime Series ForecastingMeta-Learning

    Ghent University, Research Group Data Analytics, Ghent, Belgium

  18. A Hybrid Approach to Malware Detection: Integrating Few-Shot Model-Agnostic Meta-Learning with Autoencoders

    Oct 1, 2026Emmanuela Andam, Yasir Abbas Zaidi, Abdelali Hadir +2Meta-LearningMalware Detection

    Artificial Intelligence Research (AIR) Center, University of North Dakota, Grand Forks, ND, USA · School of Electrical Engineering and Computer Science, University of North Dakota, Grand Forks, ND, USA · National School of Commerce and Management, Hassan II University, Casablanca, Morocco

  19. LARC: Low-Rank Adaptive Residual Connections for Learning in Frozen Models

    Sep 30, 2026Junyi Zou, Avrova DonzMeta-LearningResidual Learning

    MMLA-org · Communication University of China (CUC), No. 1 Dingfuzhuang East Street, Chaoyang District, Beijing 100024, China

  20. Compiling Learning Problems into Adaptation Programs for Language Models

    Sep 29, 2026Rebecca Ramnauth, Brian ScassellatiMeta-LearningLLM Fine-Tuning

    Department of Computer Science Yale University New Haven, CT 06511, USA

  21. Harness Learning Enables Generalizable Test-Time Adaptation

    Sep 28, 2026Alvin Zhang, Xuecheng Liu, Zixuan Wang +6Test-Time AdaptationMeta-Learning

  22. DGS-MLDG: Domain Gradient Surgery Guided Meta-Learning for Domain Generalization in Speech Deepfake Detection

    Sep 27, 2026Siqing Qin, Kong Aik Lee, Youzhi Tu +2Audio Deepfake DetectionMeta-Learning

    Dept. of Electrical and Electronic Engineering, The Hong Kong Polytechnic University · College of Computing and Data Science, Nanyang Technological University

  23. ABO-Med: Accelerated Bilevel Optimization for Few-Shot Medical Image Classification

    Sep 27, 2026Ruoxuan Shi, Sheng Yang, Zhengxing Su +2Few-Shot LearningMeta-Learning

    School of Mathematics and Statistics, Lanzhou University · Department of Statistics, University of California, Riverside · Department of Oncology, Lanzhou University Second Hospital

  24. Structuring Relations Among Learning Paradigms via Protocol--Objective--Resource Reductions

    Sep 26, 2026Junwei Su, Changjie Wang, Dongyang ChangStatistical Learning TheoryMeta-Learning

    University of Science and Technology of China

  25. ProTTT: Learning to Learn Semantic User Memory with Test-Time Training

    Sep 26, 2026Sejun Park, Hyoungjo Bhang, Hyein Jeong +1Personalized Language ModelsPersistent Memory for Language Models

    Graduate School of Data Science, Seoul National University

  26. RecastVLA: From Past Interaction to Future Control with Adaptive Policy States

    Sep 26, 2026Wenbo Li, Jun Yang, Yiteng Chen +2Robotic ManipulationTest-Time Adaptation of VLA Models

    School of Software Engineering, South China University of Technology Guangzhou, China · Yuanwu Technology, Shenzhen, China

  27. Online Learning via Learned Latent Bayesian Tracking

    Sep 25, 2026Guy Gerson, Tomer Raviv, Nir Shlezinger +2Online LearningBayesian Filtering

    School of ECE Ben-Gurion University Be‘er-Sheva, Israel · Institute for Intelligent Networked Systems (INSI) Northeastern University London London, U.K

  28. Online Task Adaptation via Self-Organisation

    Sep 24, 2026Krsto ProrokovićNeural Cellular AutomataMemory-Augmented Neural Networks

    Independent Researcher Montenegro

  29. NPBoost: Neural Processes with Gradient-Boosted Fixed Effects

    Sep 23, 2026Andrea Nava, Ken Rölli, Armin Begic +1Meta-LearningNeural Processes

    Seminar for Statistics, ETH Zurich, Switzerland · Lucerne University of Applied Sciences and Arts, Switzerland

  30. CORE-STACK+: Meta-Learning for Deep Stacked Generalization

    Sep 22, 2026Noor Islam S. MohammadEnsemble LearningMeta-Learning

    Department of Computer Science Istanbul Technical University Maslak, Istanbul 34469, TR