Meta-Learning

AAAI 2024arXiv:2307.16424

#2

MetaDiff: Meta-Learning with Conditional Diffusion for Few-Shot Learning

Baoquan Zhang, Chuyao Luo, Demin Yu et al.

meta-learningfew-shot learningdiffusion modelsgradient-based optimization+4

79

ICLR 2024arXiv:2310.08887

#3

METRA: Scalable Unsupervised RL with Metric-Aware Abstraction

Seohong Park, Oleh Rybkin, Sergey Levine

75

ICLR 2024arXiv:2306.04891

#4

In-Context Learning through the Bayesian Prism

Madhur Panwar, Kabir Ahuja, Navin Goyal

72

AAAI 2024arXiv:2308.14034

#5

Confucius: Iterative Tool Learning from Introspection Feedback by Easy-to-Difficult Curriculum

Zhengliang Shi, Shen Gao, Minghang Zhu et al.

72

ICLR 2025arXiv:2407.10490

#6

Learning Dynamics of LLM Finetuning

YI REN, Danica Sutherland

learning dynamicsinstruction tuningpreference tuningdirect preference optimization+4

67

ICLR 2025arXiv:2501.05707

#7

Multiagent Finetuning: Self Improvement with Diverse Reasoning Chains

Vighnesh Subramaniam, Yilun Du, Joshua B Tenenbaum et al.

63

ICLR 2025arXiv:2410.13213

#8

LLMOPT: Learning to Define and Solve General Optimization Problems from Scratch

caigao jiang, Xiang Shu, Hong Qian et al.

57

ECCV 2024arXiv:2407.06322

#9

MagMax: Leveraging Model Merging for Seamless Continual Learning

Daniel Marczak, Bartlomiej Twardowski, Tomasz Trzcinski et al.

46

CVPR 2024arXiv:2404.00851

#10

Prompt Learning via Meta-Regularization

Jinyoung Park, Juyeon Ko, Hyunwoo J. Kim

42

NEURIPS 2025arXiv:2503.09501

#11

ReMA: Learning to Meta-Think for LLMs with Multi-agent Reinforcement Learning

Ziyu Wan, Yunxiang Li, Xiaoyu Wen et al.

meta-thinkingmulti-agent reinforcement learninglarge language modelsreasoning processes+4

40

ICLR 2024arXiv:2403.13249

#12

A Unified and General Framework for Continual Learning

Zhenyi Wang, Yan Li, Li Shen et al.

40

ICLR 2025arXiv:2406.13356

#13

Unlearning or Obfuscating? Jogging the Memory of Unlearned LLMs via Benign Relearning

Shengyuan Hu, Yiwei Fu, Steven Wu et al.

40

CVPR 2024arXiv:2311.13127

#14

MetaCloak: Preventing Unauthorized Subject-driven Text-to-image Diffusion-based Synthesis via Meta-learning

Yixin Liu, Chenrui Fan, Yutong Dai et al.

37

ICML 2024arXiv:2401.15530

#15

An Information-Theoretic Analysis of In-Context Learning

Hong Jun Jeon, Jason Lee, Qi Lei et al.

in-context learninginformation-theoretic analysismeta-learning errorbayes optimal predictor+3

37

CVPR 2024arXiv:2403.02628

#16

Interactive Continual Learning: Fast and Slow Thinking

Biqing Qi, Xinquan Chen, Junqi Gao et al.

continual learningcomplementary learning systemsmultimodal large language modelsvision transformer models+4

36

ICML 2025arXiv:2412.17451

#17

Diving into Self-Evolving Training for Multimodal Reasoning

Wei Liu, Junlong Li, Xiwen Zhang et al.

29

ICML 2024arXiv:2401.14953

#18

Learning Universal Predictors

Jordi Grau-Moya, Tim Genewein, Marcus Hutter et al.

meta-learninguniversal predictionsolomonoff inductionuniversal turing machines+4

26

ICLR 2024arXiv:2310.10971

#19

Context-Aware Meta-Learning

Christopher Fifty, Dennis Duan, Ronald Junkins et al.

24

ICLR 2025arXiv:2406.09179

#20

Towards Effective Evaluations and Comparisons for LLM Unlearning Methods

Qizhou Wang, Bo Han, Puning Yang et al.

machine unlearninglarge language modelsevaluation metrics robustnessknowledge retention trade-offs+4

23

CVPR 2024arXiv:2404.00417

#21

Orchestrate Latent Expertise: Advancing Online Continual Learning with Multi-Level Supervision and Reverse Self-Distillation

Hongwei Yan, Liyuan Wang, Kaisheng Ma et al.

23

ICLR 2024arXiv:2402.05828

#22

Discovering Temporally-Aware Reinforcement Learning Algorithms

Matthew T Jackson, Chris Lu, Louis Kirsch et al.

21

NEURIPS 2025arXiv:2506.12618

#23

OpenUnlearning: Accelerating LLM Unlearning via Unified Benchmarking of Methods and Metrics

Vineeth Dorna, Anmol Mekala, Wenlong Zhao et al.

21

CVPR 2024arXiv:2312.00600

#24

Improving Plasticity in Online Continual Learning via Collaborative Learning

Maorong Wang, Nicolas Michel, Ling Xiao et al.

online continual learningcatastrophic forgettingmodel plasticitycollaborative learning+3

21

ECCV 2024arXiv:2407.10494

#25

Learning to Unlearn for Robust Machine Unlearning

Mark HUANG, Lin Geng Foo, Jun Liu

19

ICCV 2025arXiv:2410.12777

#26

Meta-Unlearning on Diffusion Models: Preventing Relearning Unlearned Concepts

Hongcheng Gao, Tianyu Pang, Chao Du et al.

diffusion modelsconcept unlearningmalicious finetuningmodel misuse prevention+3

18

ICML 2024arXiv:2402.03969

#27

In-Context Learning Agents Are Asymmetric Belief Updaters

Johannes A. Schubert, Akshay Kumar Jagadish, Marcel Binz et al.

in-context learningbelief updatinglarge language modelscognitive psychology tasks+3

16

ICLR 2024arXiv:2403.06914

#28

A Good Learner can Teach Better: Teacher-Student Collaborative Knowledge Distillation

Ayan Sengupta, Shantanu Dixit, Md Shad Akhtar et al.

MEND: Meta Demonstration Distillation for Efficient and Effective In-Context Learning

Yichuan Li, Xiyao Ma, Sixing Lu et al.

14

NEURIPS 2025arXiv:2512.24695

#30

Nested Learning: The Illusion of Deep Learning Architectures

Ali Behrouz, Meisam Razaviyayn, Peilin Zhong et al.

nested learning paradigmin-context learningexpressive optimizersassociative memory modules+4

14

ICLR 2024arXiv:2403.09859

#31

MAMBA: an Effective World Model Approach for Meta-Reinforcement Learning

Zohar Rimon, Tom Jurgenson, Orr Krupnik et al.

14

ICLR 2025arXiv:2410.06209

#32

LeanAgent: Lifelong Learning for Formal Theorem Proving

Adarsh Kumarappan, Mohit Tiwari, Peiyang Song et al.

formal theorem provinglifelong learningcurriculum learningmathematical reasoning+4

12

ICLR 2025arXiv:2412.16577

#33

A Meta-Learning Approach to Bayesian Causal Discovery

Anish Dhir, Matthew Ashman, James Requeima et al.

causal discoverybayesian posteriormeta-learningcausal structure+2

12

AAAI 2025arXiv:2412.07507

#34

ConfigX: Modular Configuration for Evolutionary Algorithms via Multitask Reinforcement Learning

Hongshu Guo, Zeyuan Ma, Jiacheng Chen et al.

modular configurationevolutionary algorithmsmultitask reinforcement learningblack-box optimization+4

12

ICLR 2024arXiv:2506.10629

#35

Knowledge-Aware Parameter Coaching for Personalized Federated Learning

Mingjian Zhi, Yuanguo Bi, Wenchao Xu et al.

Task Adaptation from Skills: Information Geometry, Disentanglement, and New Objectives for Unsupervised Reinforcement Learning

Yucheng Yang, Tianyi Zhou, Qiang HE et al.

11

ICML 2024arXiv:2402.04054

#37

More Flexible PAC-Bayesian Meta-Learning by Learning Learning Algorithms

Hossein Zakerinia, Amin Behjati, Christoph Lampert

pac-bayesian theorymeta-learning frameworkknowledge transferlearning algorithm learning+2

10

NEURIPS 2025arXiv:2505.22453

#38

First SFT, Second RL, Third UPT: Continual Improving Multi-Modal LLM Reasoning via Unsupervised Post-Training

Lai Wei, Yuting Li, Chen Wang et al.

multi-modal large language modelsunsupervised post-trainingself-rewarding mechanismmajority voting+3

10

ICLR 2024arXiv:2312.00477

#39

Interpretable Meta-Learning of Physical Systems

Matthieu Blanke, marc lelarge

10

CVPR 2024arXiv:2405.00984

#40

FREE: Faster and Better Data-Free Meta-Learning

Yongxian Wei, Zixuan Hu, Zhenyi Wang et al.

9

NEURIPS 2025arXiv:2506.05735

#41

Do LLMs Really Forget? Evaluating Unlearning with Knowledge Correlation and Confidence Awareness

Rongzhe Wei, Peizhi Niu, Hans Hao-Hsun Hsu et al.

machine unlearningknowledge graphslarge language modelsinferential dependencies+3

9

ICLR 2025arXiv:2412.08021

#42

Can a MISL Fly? Analysis and Ingredients for Mutual Information Skill Learning

Chongyi Zheng, Jens Tuyls, Joanne Peng et al.

mutual information skill learningcontrastive representation learningsuccessor featuresself-supervised learning+3

9

ICML 2025arXiv:2505.16694

#43

Beyond Induction Heads: In-Context Meta Learning Induces Multi-Phase Circuit Emergence

Gouki Minegishi, Hiroki Furuta, Shohei Taniguchi et al.

ICML 2024arXiv:2405.18758

#44

Learning to Continually Learn with the Bayesian Principle

Soochan Lee, Hyeonseong Jeon, Jaehyeon Son et al.

continual learningbayesian updatingmeta-learningcatastrophic forgetting+4

ICLR 2025arXiv:2410.05434

#45

Better than Your Teacher: LLM Agents that learn from Privileged AI Feedback

Sanjiban Choudhury, Paloma Sodhi

ICML 2025arXiv:2505.02010

#46

Meta-Black-Box-Optimization through Offline Q-function Learning

Zeyuan Ma, Zhiguang Cao, Zhou Jiang et al.

NEURIPS 2025arXiv:2506.00359

#47

Keeping an Eye on LLM Unlearning: The Hidden Risk and Remedy

Jie Ren, Zhenwei Dai, Xianfeng Tang et al.

large language modelsmachine unlearningadversarial attacksmodel utility degradation+3

ICML 2025arXiv:2506.11672

#48

Dynamic Mixture of Curriculum LoRA Experts for Continual Multimodal Instruction Tuning

Chendi Ge, Xin Wang, Zeyang Zhang et al.

ICCV 2025arXiv:2508.02293

#49

Towards Real Unsupervised Anomaly Detection Via Confident Meta-Learning

Muhammad Aqeel, Shakiba Sharifi, Marco Cristani et al.

unsupervised anomaly detectionconfident meta-learningsoft confident learningmeta-learning regularization+3

ICML 2025arXiv:2505.05279

#50

MTL-UE: Learning to Learn Nothing for Multi-Task Learning

Yi Yu, Song Xia, SIYUAN YANG et al.

NEURIPS 2025arXiv:2505.17895

#51

DataRater: Meta-Learned Dataset Curation

Dan Andrei Calian, Greg Farquhar, Iurii Kemaev et al.

dataset curationmeta-learningmeta-gradientstraining efficiency+3

ICML 2024arXiv:2310.15047

#52

Implicit meta-learning may lead language models to trust more reliable sources

Dmitrii Krasheninnikov, Egor Krasheninnikov, Bruno Mlodozeniec et al.

implicit meta-learninglarge language modelsdocument usefulness indicatorsfine-tuning datasets+3

NEURIPS 2025arXiv:2505.10425

#53

Learning to Think: Information-Theoretic Reinforcement Fine-Tuning for LLMs

Jingyao Wang, Wenwen Qiang, Zeen Song et al.

6

AAAI 2024arXiv:2312.06518

#54

Decoupling Meta-Reinforcement Learning with Gaussian Task Contexts and Skills

Hongcai He, Anjie Zhu, Shuang Liang et al.

self-playcalibrationtool usemultiagent

#55

Don’t lie to your friends: Learning what you know from collaborative self-play

Jacob Eisenstein, Reza Aghajani, Adam Fisch et al.

COLM 2025

NEURIPS 2025arXiv:2505.09666

#56

System Prompt Optimization with Meta-Learning

Yumin Choi, Jinheon Baek, Sung Ju Hwang

system prompt optimizationmeta-learning frameworkbilevel optimizationprompt transferability+4

AAAI 2024arXiv:2312.15340

#57

Meta-Learning-Based Adaptive Stability Certificates for Dynamical Systems

Authors: Amit Jena, Dileep Kalathil, Le Xie

NEURIPS 2025arXiv:2505.17010

#58

Understanding Prompt Tuning and In-Context Learning via Meta-Learning

Tim Genewein, Kevin Li, Jordi Grau-Moya et al.

prompt tuningin-context learningmeta-learningbayesian predictors+4

NEURIPS 2025arXiv:2506.17859

#59

In-Context Learning Strategies Emerge Rationally

Daniel Wurgaft, Ekdeep S Lubana, Core Francisco Park et al.

in-context learningbayesian predictorstransformer predictionshierarchical bayesian framework+4

AAAI 2024arXiv:2303.01074

#60

Learning Not to Regret

David Sychrovský, Michal Sustr, Elnaz Davoodi et al.

ECCV 2024arXiv:2410.11878

#61

Neural Metamorphosis

Xingyi Yang, Xinchao Wang

neural implicit functionsweight manifold learninghypernetworksmodel compression+3

ICML 2025arXiv:2502.07709

#62

MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces

Loris Gaven, Thomas Carta, Clément Romac et al.

CVPR 2025arXiv:2503.18987

#63

Balanced Direction from Multifarious Choices: Arithmetic Meta-Learning for Domain Generalization

Xiran Wang, Jian Zhang, Lei Qi et al.

domain generalizationdistribution shiftmeta-learning algorithmsgradient matching theory+3

ICLR 2025arXiv:2505.00031

#64

Learning to Plan Before Answering: Self-Teaching LLMs to Learn Abstract Plans for Problem Solving

Jin Zhang, Flood Sung, Zhilin Yang et al.

ICCV 2025arXiv:2502.20158

#65

Learning to Generalize without Bias for Open-Vocabulary Action Recognition

Yating Yu, Congqi Cao, Yifan Zhang et al.

open-vocabulary action recognitionvisual-text alignmentstatic bias debiasingmeta-learning framework+3

ICML 2024arXiv:2403.08477

#66

Unleashing the Power of Meta-tuning for Few-shot Generalization Through Sparse Interpolated Experts

Shengzhuang Chen, Jihoon Tack, Yunqiao Yang et al.

meta-tuningfew-shot generalizationsparse mixture-of-expertsout-of-distribution generalization+3

NEURIPS 2025arXiv:2505.22310

#67

From Dormant to Deleted: Tamper-Resistant Unlearning Through Weight-Space Regularization

Shoaib Ahmed Siddiqui, Adrian Weller, David Krueger et al.

ICLR 2024arXiv:2212.01168

#68

Towards Cross Domain Generalization of Hamiltonian Representation via Meta Learning

Yeongwoo Song, Hawoong Jeong

ICCV 2025arXiv:2503.06339

#69

Learning to Unlearn while Retaining: Combating Gradient Conflicts in Machine Unlearning

Gaurav Patel, Qiang Qiu

AAAI 2024arXiv:2403.03082

#70

Recall-Oriented Continual Learning with Generative Adversarial Meta-Model

Haneol Kang, Dong-Wan Choi

continual learningstability-plasticity dilemmagenerative adversarial meta-modelrecall-oriented framework+3

AAAI 2025arXiv:2412.13790

#71

Toward Efficient Data-Free Unlearning

Chenhao Zhang, Shaofei Shen, Weitong Chen et al.

machine unlearningdata-free distillationsynthetic sample generationknowledge retention+1

NEURIPS 2025arXiv:2507.01649

#72

GradMetaNet: An Equivariant Architecture for Learning on Gradients

Yoav Gelberg, Yam Eitan, Aviv Navon et al.

equivariant architecturegradient processinglearned optimizationneuron permutation symmetry+4

ICLR 2025arXiv:2405.16124

#73

Unsupervised Meta-Learning via In-Context Learning

Anna Vettoruzzo, Lorenzo Braccaioli, Joaquin Vanschoren et al.

unsupervised meta-learningin-context learningtransformer architecturessequence modeling+4

ECCV 2024arXiv:2407.08411

#74

CLEO: Continual Learning of Evolving Ontologies

Shishir Muralidhara, Saqib Bukhari, Georg Dr. Schneider et al.

continual learningcatastrophic forgettingevolving ontologiesclass-incremental learning+3

ICLR 2025arXiv:2402.16105

#75

Towards Automated Knowledge Integration From Human-Interpretable Representations

Katarzyna Kobalczyk, Mihaela van der Schaar

NEURIPS 2025arXiv:2506.13464

#76

Unveiling the Learning Mind of Language Models: A Cognitive Framework and Empirical Study

Zhengyu Hu, Jianxun Lian, Zheyuan Xiao et al.

language model learningcognitive psychology frameworkknowledge acquisitionconceptual generalization+3

ICLR 2025arXiv:2410.08355

#77

Metalic: Meta-Learning In-Context with Protein Language Models

Jacob Beck, Shikha Surana, Manus McAuliffe et al.

machine unlearningdata attributionforget set removalmodel fine-tuning+3

#78

Machine Unlearning via Simulated Oracle Matching

Kristian G Georgiev, Roy Rinberg, Sam Park et al.

ICLR 2025

ICML 2025arXiv:2402.02342

#79

MetaOptimize: A Framework for Optimizing Step Sizes and Other Meta-parameters

Arsalan Sharifnassab, Saber Salehkaleybar, Rich Sutton

ICML 2025arXiv:2505.00793

#80

Scalable Meta-Learning via Mixed-Mode Differentiation

Iurii Kemaev, Dan Andrei Calian, Luisa Zintgraf et al.

ICML 2025arXiv:2212.14681

#81

An Entropy-Based Model for Hierarchical Learning

Amir R. Asadi

ICLR 2025arXiv:2505.10941

#82

Privacy-Aware Lifelong Learning

Ozan Özdenizci, Elmar Rueckert, Robert Legenstein

ICML 2025arXiv:2503.01885

#83

Learning Policy Committees for Effective Personalization in MDPs with Diverse Tasks

Luise Ge, Michael Lanier, Anindya Sarkar et al.

AAAI 2025arXiv:2503.23390

#84

Pareto Continual Learning: Preference-Conditioned Learning and Adaption for Dynamic Stability-Plasticity Trade-off

Song Lai, Zhe Zhao, Fei Zhu et al.

AAAI 2024arXiv:2301.02761

#85

Active Learning Guided by Efficient Surrogate Learners

Yunpyo An, Suyeong Park, Kwang In Kim

active learningbatch-based samplinggaussian process surrogatesurrogate learners+3

AAAI 2025arXiv:2410.10417

#86

A Stochastic Approach to Bi-Level Optimization for Hyperparameter Optimization and Meta Learning

Minyoung Kim, Timothy Hospedales

bi-level optimizationhyperparameter optimizationmeta learningstochastic gradient langevin dynamics+3

AAAI 2024arXiv:2401.05097

#87

Any-Way Meta Learning

JunHoo Lee, Yearim Kim, Hyunho Lee et al.

meta learninglabel equivalenceany-way learningdomain generalization+4

ICML 2024arXiv:2307.03565

#88

MALIBO: Meta-learning for Likelihood-free Bayesian Optimization

Jiarong Pan, Stefan Falkner, Felix Berkenkamp et al.

bayesian optimizationmeta-learninglikelihood-free inferenceblack-box optimization+3

COLM 2025arXiv:2508.06595

#89

LLM Unlearning Without an Expert Curated Dataset

Xiaoyuan Zhu, Muru Zhang, Ollie Liu et al.

NLPMachine UnlearningSynthetic Data Generation

NEURIPS 2025arXiv:2510.17210

#90

Learning on the Go: A Meta-learning Object Navigation Model

Xiaorong Qin, Xinhang Song, Sixian Zhang et al.

Meta-Learning Hyperparameters for Parameter Efficient Fine-Tuning

Zichen Tian, Yaoyao Liu, Qianru Sun

Wisdom is Knowing What not to Say: Hallucination-Free LLMs Unlearning via Attention Shifting

Chenchen Tan, Youyang Qu, Xinghao Li et al.

AAAI 2025arXiv:2412.12030

#93

Memory-Reduced Meta-Learning with Guaranteed Convergence

Honglin Yang, Ji Ma, Xiao Yu

meta-learningoptimization-based meta-learningmemory reductiongradient estimation+2

NEURIPS 2025arXiv:2510.23013

#94

MoEMeta: Mixture-of-Experts Meta Learning for Few-Shot Relational Learning

Han Wu, Jie Yin

few-shot learningknowledge graph reasoningrelational learningmixture-of-experts models+4

sensory cortexrepresentation learningmargin maximizationneural data analysis+3

#95

Do Mice Grok? Glimpses of Hidden Progress in Sensory Cortex

Tanishq Kumar, Blake Bordelon, Cengiz Pehlevan et al.

ICLR 2025

NEURIPS 2025arXiv:2510.19797

#96

Transformers are almost optimal metalearners for linear classification

Roey Magen, Gal Vardi

in-context learningmetalearninglinear classificationtransformer architecture+3

NEURIPS 2025arXiv:2503.18403

#97

Knowledge Graph Enhanced Generative Multi-modal Models for Class-Incremental Learning

Xusheng Cao, Haori Lu, Linlan Huang et al.

knowledge graph enhancementclass-incremental learningcatastrophic forgettingmulti-modal models+3

ICML 2025arXiv:2410.13577

#98

Generalization Bounds via Meta-Learned Model Representations: PAC-Bayes and Sample Compression Hypernetworks

Benjamin Leblanc, Mathieu Bazinet, Nathaniel D'Amours et al.

#99

Empowering Self-Learning of LLMs: Inner Knowledge Explicitation as a Catalyst

Shijue Huang, Wanjun Zhong, Deng Cai et al.

Meta-Learning Dynamic Center Distance: Hard Sample Mining for Learning with Noisy Labels

Chenyu Mu, Yijun Qu, Jiexi Yan et al.

ICCV 2025