Meta-Learning

Follow this topic Ask about this topic

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

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

Learning Cardiac Motion Priors for Implicit Neural Representations
Jul 1, 2026Andrew Bell, George Webber, Andrew P King +3Implicit Neural Representations Meta-Learning
School of Biomedical Engineering and Imaging Sciences, King’s College London, United Kingdom · William Harvey Research Institute, Queen Mary University of London,2026 United Kingdom · Cardio-Oncology Service, Royal Brompton and Harefield Hospitals, London, United Kingdom
Human-Machine Collaboration on Generative Meta-Learning: Model and Algorithm
Jul 1, 2026Midhun Parakkal Unni, Samuel KaskiMeta-Learning Synthetic Data Generation
School of Computer Science, University of Sheffield, Sheffield, UK · Centre for Machine intelligence, University of Sheffield, UK · Department of Computer Science, University of Manchester, Manchester, UK +2
Meta-Transfer Learning for mmWave Beam Alignment
Jul 1, 2026Ahmet Nuri Cevik, Sinem ColeriMeta-Learning Wireless Communications
From Search to Synthesis: Training LLMs as Zero-Shot Workflow Generators
Jun 29, 2026Gan Luo, Zihan Qin, Bin Dong +1Zero-Shot Learning Meta-Learning
School of Mathematics Science, Peking University
Meta-learning as a principle for human-like visual representations
Jun 24, 2026Can Demircan, Marcel Binz, Alireza Modirshanechi +1Visual Representation Learning Meta-Learning
Helmholtz Munich, Munich, Germany · Max Planck Institute for Biological Cybernetics, Tübingen, Germany
Extreme Meta-Classification for Large-Scale Zero-Shot Retrieval
Jun 23, 2026Sachin Yadav, Deepak Saini, Anirudh Buvanesh +6Zero-Shot Learning Meta-Learning
Microsoft Research · Microsoft · Indian Institute of Technology
Learning Dynamical Systems from Multiple Sparse Datasets: A Hierarchical Bayesian Modeling Approach
Jun 23, 2026Cristian Brugnara, Lea Multerer, Marco Forgione +1Irregular Time-Series Modeling Parameter Estimation
SUPSI, Dalle Molle Institute for Artificial Intelligence (IDSIA USI-SUPSI), Lugano, Switzerland
Exploring Dualistic Meta-Learning to Enhance Domain Generalization in Open Set Scenarios
Jun 22, 2026Xiran Wang, Jian Zhang, Lei Qi +2Meta-Learning Domain Generalization
State Key Laboratory for Novel Software Technology, Nanjing University, China · School of Computer Science and Engineering, Southeast University, China
CIWI-CKT: Chaos-Informed Wave Interference Feature Fusion and Cross-City Knowledge Transfer for Traffic Flow Forecasting
Jun 14, 2026Abdul Joseph Fofanah, Lian Wen, David Chen +1Meta-Learning Few-Shot Learning
School of Information and Communication Technology, Griffith University, Brisbane, 4111, Australia · School of Information Engineering, Chang’an University, Xi’an, China
A Guide to Estimating Conditional Average Treatment Effects in Competing Risks Settings
Jun 8, 2026Daniel Klippert, Sarah Friedrich, Markus PaulyCausal Effect Estimation Meta-Learning
Department of Statistics, TU Dortmund University · Research Center Trustworthy Data Science and Security, University Alliance Ruhr (UA Ruhr) · Institute for Mathematics, University of Augsburg
CoMetaPNS: Continually Meta-learning Personalized Neural Surrogates for Cardiac Electrophysiology Simulations
Jun 5, 2026Ryan Missel, Xiajun Jiang, Linwei WangNeural Surrogate Modeling Surrogate Modeling
Robotic Policy Adaptation via Weight-Space Meta-Learning
Jun 5, 2026Christian Bianchi, Siamak Yousefi, Alessio Sampieri +4Robot Policy Adaptation Robot Skill Learning
ItalAI · ItalAI and Sapeinza University of Rome
Learning to Route LLMs from Implicit Cost-Performance Preferences via Meta-Learning
Jun 4, 2026Jiahao Zeng, Ming Tang, Ningning DingMeta-Learning Cost-Aware Inference
Hong Kong University of Science and Technology (Guangzhou) · Southern University of Science and Technology
R-APS: Compositional Reasoning and In-Context Meta-Learning for Constrained Design via Reflective Adversarial Pareto Search
Jun 3, 2026João Pedro Gandarela, Thiago Rios, Stefan Menzel +1Mechanism Design Meta-Learning
Idiap Research Institute, Switzerland · École Polytechnique Fédérale de Lausanne (EPFL), Switzerland · Honda Research Institute Europe, Germany +2
Bayesian meta-learning for modeling Alzheimer's disease progression
Jun 1, 2026Clara Hoffmann, Nadja KleinAlzheimer's Disease Meta-Learning
Scientific Computing Center, Karlsruhe Institute of Technology, Germany
Provable Data Scaling Law for Meta Learning via Complexity Minimization
Jun 1, 2026Kazuto Fukuchi, Ryuichiro Hataya, Kota MatsuiMeta-Learning Few-Shot Learning
University of Tsukuba, Japan · RIKEN AIP, Japan · SB Intuitions Corp., Japan +3
UME: A Unified Meta-Generalization Framework for Cross-Domain ETA
May 31, 2026Duo Wang, Qiong Wu, Jianguo Wu +9Event Time Prediction Meta-Learning
Peking University · Meituan
On the Difficulty of Learning a Meta-network for Training Data Selection
May 30, 2026Zilin Du, Junqi Zhao, Boyang Albert LiMeta-Learning Training Data Selection
College of Computing and Data Science, Nanyang Technological University, Singapore.
CHAM-net: A Contrastive Hierarchical Adaptive Meta-network for Robust Global Methane Flux Prediction
May 29, 2026Rongchao Dong, Yiming Sun, Shuo Chen +4Meta-Learning Spatiotemporal Forecasting
University of Pittsburgh · Purdue University · University of Colorado Boulder +3
You Live More Than Once: Towards Hierarchical Skill Meta-Evolving
May 27, 2026Xujun Li, Kehan Zheng, Mingyuan Zhao +7Meta-Learning LLM Agent Skill Learning
Department of Computer Science and Technology, Tsinghua University · Huawei Foundation Model Department
Advancing Graph Few-Shot Learning via In-Context Learning
May 23, 2026Renchu Guan, Yajun Wang, Chunli Guo +5Meta-Learning Few-Shot Learning
Key Laboratory of Symbolic Computation and Knowledge Engineering of the Ministry of Education
Meta-Learning for Rapid Adaptation in Reference Tracking of Uncertain Nonlinear Systems
May 21, 2026Jiaqi Yan, Ankush Chakrabarty, Niklas Schmid +2Robot Trajectory Tracking Meta-Learning
School of Automation Science and Electrical Engineering, Beihang University, Beijing 100191, P. R. China · Mitsubishi Electric Research Laboratories, Cambridge, MA 02139, USA · Automatic Control Laboratory, ETH Zurich, Switzerland +1
ForeSplat: Optimization-Aware Foresight for Feed-Forward 3D Gaussian Splatting
May 21, 2026Yuke Li, Weihang Liu, Cheng Zhang +83D Gaussian Splatting Meta-Learning
ShanghaiTech University · GGU Technology Co., Ltd · Stereye
Cumulative Meta-Learning from Active Learning Queries for Robustness to Spurious Correlations
May 20, 2026Kin Whye Chew, Jingxian WangMeta-Learning Active Learning
Department of Computer Science National University of Singapore Singapore, S119077
MANGO: Meta-Adaptive Network Gradient Optimization for Online Continual Learning
May 18, 2026Ankita Awasthi, Marco Apolinario, Kaushik RoyClass-Incremental Learning Meta-Learning
Purdue University, USA · TU Delft, Netherlands
Efficient Bilevel Optimization for Meta Label Correction in Noisy Label Learning
May 18, 2026Ba Hoang Anh Nguyen, Viet Cuong TaMeta-Learning Noisy-Label Learning
Human-Machine Interaction Laboratory, VNU University of Engineering and Technology, Hanoi, Vietnam
Boundedly Rational Meta-Learning in Sequential Consumer Choice
May 15, 2026Mehrzad Khosravi, Max Kleiman-Weiner, Hema YoganarasimhanMeta-Learning Sequential Decision Making
University of Washington
EUPHORIA: Efficient Universal Planning via Hybrid Optimization for Robust Industrial Robotic Assembly
May 15, 2026Shih-Yu Lai, Chia-Ching Yen, Yang-Ting Shen +3Robotic Construction Meta-Learning
National Taiwan University · MoonShine Animation Studio · National Cheng Kung University +2
Seeking the Unfamiliar but Memorable: Conceptual Creativity as Meta-Learning
May 15, 2026Mengye RenMeta-Learning Computational Creativity
Agentic Learning AI Lab, New York University
Learn2Splat: Extending the Horizon of Learned 3DGS Optimization
May 15, 2026Naama Pearl, Stefano Esposito, Haofei Xu +63D Gaussian Splatting Meta-Learning
University of Tübingen, Tübingen AI Center · ETH Zurich · Meta Reality Labs

Jul 1, 2026J/K move · Enter open · S save

Learning Cardiac Motion Priors for Implicit Neural Representations

Andrew Bell, George Webber, Andrew P King, Steffen E Petersen+2

School of Biomedical Engineering and Imaging Sciences, King’s College London, United Kingdom · William Harvey Research Institute, Queen Mary University of London,2026 United Kingdom · Cardio-Oncology Service, Royal Brompton and Harefield Hospitals, London, United Kingdom

Implicit Neural Representations Meta-Learning Medical Image Analysis Cardiac MRI

Open paper AskPDF arXiv

Implicit neural representations (INRs) are well suited to cardiac motion estimation, providing continuous, compact representations of motion fields. However, fitting an INR to each image sequence is time-consuming and sensitive to the optimisation trajectory. Learned priors can help guide optimisation towards plausible motion fields and enable faster adaptation, but learning priors for cardiac motion INRs remains under-explored. In this work, we compare four strategies for learning cardiac motion priors, including a population prior learned by joint optimisation, a consensus prior obtained by weight averaging, auto-decoders, and meta-learning. Using short-axis tagged cardiac magnetic resonance images from the UK Biobank, we evaluate their impact on tracking accuracy, motion behaviour, and adaptation trajectory. All learned priors substantially improved early adaptation performance compared with random initialisation. While the simple consensus prior was effective, auto-decoders recovered large deformations faster during early adaptation. Meta-learning achieved strong early performance and maintained the best adaptation trajectory over 50 iterations.