🧬Learning Paradigms

Meta-Learning

Learning to learn

100 papers5,609 total citations
Compare with other topics
Feb '24 Jan '26840 papers
Also includes: meta-learning, meta learning, learning to learn, maml, metalearning

Top Papers

#1

YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information

Chien-Yao Wang, I-Hau Yeh, Hong-Yuan Mark Liao

ECCV 2024arXiv:2402.13616
programmable gradient informationinformation bottleneckreversible functionsgradient path planning+4
2,952
citations
#2

SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation

Chongyu Fan, Jiancheng Liu, Yihua Zhang et al.

ICLR 2024
263
citations
#3

Fast Machine Unlearning without Retraining through Selective Synaptic Dampening

Jack Foster, Stefan Schoepf, Alexandra Brintrup

AAAI 2024arXiv:2308.07707
machine unlearningselective synaptic dampeningfisher information matrixpost hoc unlearning+3
170
citations
#4

MUSE: Machine Unlearning Six-Way Evaluation for Language Models

Weijia Shi, Jaechan Lee, Yangsibo Huang et al.

ICLR 2025arXiv:2407.06460
machine unlearninglanguage modelsprivacy leakageverbatim memorization+4
157
citations
#5

Synapse: Trajectory-as-Exemplar Prompting with Memory for Computer Control

Longtao Zheng, Rundong Wang, Xinrun Wang et al.

ICLR 2024
103
citations
#6

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

Baoquan Zhang, Chuyao Luo, Demin Yu et al.

AAAI 2024arXiv:2307.16424
meta-learningfew-shot learningdiffusion modelsgradient-based optimization+4
76
citations
#7

MAVIS: Mathematical Visual Instruction Tuning with an Automatic Data Engine

Renrui Zhang, Xinyu Wei, Dongzhi Jiang et al.

ICLR 2025
74
citations
#8

METRA: Scalable Unsupervised RL with Metric-Aware Abstraction

Seohong Park, Oleh Rybkin, Sergey Levine

ICLR 2024
68
citations
#9

Grokking as the transition from lazy to rich training dynamics

Tanishq Kumar, Blake Bordelon, Samuel Gershman et al.

ICLR 2024
63
citations
#10

Learning Dynamics of LLM Finetuning

YI REN, Danica Sutherland

ICLR 2025
61
citations
#11

LaneSegNet: Map Learning with Lane Segment Perception for Autonomous Driving

Tianyu Li, Peijin Jia, Bangjun Wang et al.

ICLR 2024
60
citations
#12

Position: The No Free Lunch Theorem, Kolmogorov Complexity, and the Role of Inductive Biases in Machine Learning

Micah Goldblum, Marc Finzi, Keefer Rowan et al.

ICML 2024
no free lunch theoremskolmogorov complexityinductive biasessupervised learning+4
60
citations
#13

OMNI-EPIC: Open-endedness via Models of human Notions of Interestingness with Environments Programmed in Code

Maxence Faldor, Jenny Zhang, Antoine Cully et al.

ICLR 2025
44
citations
#14

Class-Incremental Learning with CLIP: Adaptive Representation Adjustment and Parameter Fusion

Linlan Huang, Xusheng Cao, Haori Lu et al.

ECCV 2024arXiv:2407.14143
class-incremental learningvision-language pre-trainingrepresentation adjustmentparameter fusion+3
41
citations
#15

Prompt Learning via Meta-Regularization

Jinyoung Park, Juyeon Ko, Hyunwoo J. Kim

CVPR 2024
40
citations
#16

Self-Evolving Multi-Agent Collaboration Networks for Software Development

Yue Hu, Yuzhu Cai, Yaxin Du et al.

ICLR 2025
40
citations
#17

Combining Induction and Transduction for Abstract Reasoning

Wen-Ding Li, Keya Hu, Carter Larsen et al.

ICLR 2025
38
citations
#18

A Unified and General Framework for Continual Learning

Zhenyi Wang, Yan Li, Li Shen et al.

ICLR 2024
37
citations
#19

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

Ziyu Wan, Yunxiang Li, Xiaoyu Wen et al.

NeurIPS 2025arXiv:2503.09501
meta-thinkingmulti-agent reinforcement learninglarge language modelsreasoning processes+4
36
citations
#20

Interactive Continual Learning: Fast and Slow Thinking

Biqing Qi, Xinquan Chen, Junqi Gao et al.

CVPR 2024
35
citations
#21

Selective Forgetting: Advancing Machine Unlearning Techniques and Evaluation in Language Models

Lingzhi Wang, Xingshan Zeng, Jinsong Guo et al.

AAAI 2025
33
citations
#22

Machine Unlearning Fails to Remove Data Poisoning Attacks

Martin Pawelczyk, Jimmy Di, Yiwei Lu et al.

ICLR 2025
28
citations
#23

eTag: Class-Incremental Learning via Embedding Distillation and Task-Oriented Generation

Libo Huang, Yan Zeng, Chuanguang Yang et al.

AAAI 2024
26
citations
#24

Cascade Prompt Learning for Visual-Language Model Adaptation

Ge Wu, Xin Zhang, Zheng Li et al.

ECCV 2024
24
citations
#25

Context-Aware Meta-Learning

Christopher Fifty, Dennis Duan, Ronald Junkins et al.

ICLR 2024
24
citations
#26

Unknown Prompt the only Lacuna: Unveiling CLIP's Potential for Open Domain Generalization

Mainak Singha, Ankit Jha, Shirsha Bose et al.

CVPR 2024
23
citations
#27

ICLR: In-Context Learning of Representations

Core Francisco Park, Andrew Lee, Ekdeep Singh Lubana et al.

ICLR 2025
23
citations
#28

Self-Consistency Preference Optimization

Archiki Prasad, Weizhe Yuan, Richard Yuanzhe Pang et al.

ICML 2025
23
citations
#29

Non-exemplar Online Class-Incremental Continual Learning via Dual-Prototype Self-Augment and Refinement

Fushuo Huo, Wenchao Xu, Jingcai Guo et al.

AAAI 2024arXiv:2303.10891
class-incremental learningcontinual learningcatastrophic forgettingprototype alignment+4
23
citations
#30

Enigmata: Scaling Logical Reasoning in Large Language Models with Synthetic Verifiable Puzzles

Jiangjie Chen, Qianyu He, Siyu Yuan et al.

NeurIPS 2025
23
citations
#31

CARP: Visuomotor Policy Learning via Coarse-to-Fine Autoregressive Prediction

Zhefei Gong, Pengxiang Ding, Shangke Lyu et al.

ICCV 2025
23
citations
#32

LiNeS: Post-training Layer Scaling Prevents Forgetting and Enhances Model Merging

Ke Wang, Nikos Dimitriadis, Alessandro Favero et al.

ICLR 2025
23
citations
#33

From Lazy to Rich: Exact Learning Dynamics in Deep Linear Networks

Clementine Domine, Nicolas Anguita, Alexandra M Proca et al.

ICLR 2025
22
citations
#34

G-Memory: Tracing Hierarchical Memory for Multi-Agent Systems

Guibin Zhang, Muxin Fu, Kun Wang et al.

NeurIPS 2025
22
citations
#35

Towards Scalable Exact Machine Unlearning Using Parameter-Efficient Fine-Tuning

Somnath Basu Roy Chowdhury, Krzysztof Choromanski, Arijit Sehanobish et al.

ICLR 2025arXiv:2406.16257
machine unlearningexact unlearningparameter-efficient fine-tuningparameter isolation+4
22
citations
#36

Towards Robust Knowledge Unlearning: An Adversarial Framework for Assessing and Improving Unlearning Robustness in Large Language Models

Hongbang Yuan, Zhuoran Jin, Pengfei Cao et al.

AAAI 2025
22
citations
#37

Reinforced Lifelong Editing for Language Models

Zherui Li, Houcheng Jiang, Hao Chen et al.

ICML 2025
21
citations
#38

MLP Can Be A Good Transformer Learner

Sihao Lin, Pumeng Lyu, Dongrui Liu et al.

CVPR 2024
20
citations
#39

SelEx: Self-Expertise in Fine-Grained Generalized Category Discovery

Sarah Rastegar, Mohammadreza Salehi, Yuki M Asano et al.

ECCV 2024arXiv:2408.14371
generalized category discoveryfine-grained categorizationself-expertise learninghierarchical pseudo-labeling+2
20
citations
#40

Improving Plasticity in Online Continual Learning via Collaborative Learning

Maorong Wang, Nicolas Michel, Ling Xiao et al.

CVPR 2024
20
citations
#41

GOAL: A Generalist Combinatorial Optimization Agent Learner

Darko Drakulić, Sofia Michel, Jean-Marc Andreoli

ICLR 2025
20
citations
#42

To Grok or not to Grok: Disentangling Generalization and Memorization on Corrupted Algorithmic Datasets

Darshil Doshi, Aritra Das, Tianyu He et al.

ICLR 2024
19
citations
#43

Task-driven Image Fusion with Learnable Fusion Loss

Haowen Bai, Jiangshe Zhang, Zixiang Zhao et al.

CVPR 2025
19
citations
#44

Towards Effective Evaluations and Comparisons for LLM Unlearning Methods

Qizhou Wang, Bo Han, Puning Yang et al.

ICLR 2025
18
citations
#45

Class Incremental Learning via Likelihood Ratio Based Task Prediction

Haowei Lin, Yijia Shao, Weinan Qian et al.

ICLR 2024
18
citations
#46

Progress or Regress? Self-Improvement Reversal in Post-training

Ting Wu, Xuefeng Li, Pengfei Liu

ICLR 2025
18
citations
#47

Meta-Unlearning on Diffusion Models: Preventing Relearning Unlearned Concepts

Hongcheng Gao, Tianyu Pang, Chao Du et al.

ICCV 2025arXiv:2410.12777
diffusion modelsconcept unlearningmalicious finetuningmodel misuse prevention+3
17
citations
#48

Mixture of Noise for Pre-Trained Model-Based Class-Incremental Learning

Kai Jiang, Zhengyan Shi, Dell Zhang et al.

NeurIPS 2025
16
citations
#49

Closed-Form Merging of Parameter-Efficient Modules for Federated Continual Learning

Riccardo Salami, Pietro Buzzega, Matteo Mosconi et al.

ICLR 2025
16
citations
#50

Model Swarms: Collaborative Search to Adapt LLM Experts via Swarm Intelligence

Shangbin Feng, Zifeng Wang, Yike Wang et al.

ICML 2025
16
citations
#51

Learning to Optimize Permutation Flow Shop Scheduling via Graph-Based Imitation Learning

Longkang Li, Siyuan Liang, Zihao Zhu et al.

AAAI 2024arXiv:2210.17178
permutation flow shop schedulinggraph-based imitation learningmanufacturing systems optimizationlarge-scale scheduling problems+4
16
citations
#52

Apollo-MILP: An Alternating Prediction-Correction Neural Solving Framework for Mixed-Integer Linear Programming

Haoyang Liu, Jie Wang, Zijie Geng et al.

ICLR 2025arXiv:2503.01129
mixed-integer linear programmingneural solving frameworktrust-region searchproblem reduction+4
15
citations
#53

AutoToM: Scaling Model-based Mental Inference via Automated Agent Modeling

Zhining Zhang, Chuanyang Jin, Mung Yao Jia et al.

NeurIPS 2025
15
citations
#54

History Matters: Temporal Knowledge Editing in Large Language Model

Xunjian Yin, Jin Jiang, Liming Yang et al.

AAAI 2024arXiv:2312.05497
temporal knowledge editinglarge language modelsknowledge updatingcatastrophic forgetting+4
15
citations
#55

Learning MDL Logic Programs from Noisy Data

Céline Hocquette, Andreas Niskanen, Matti Järvisalo et al.

AAAI 2024arXiv:2308.09393
inductive logic programmingminimal description lengthnoisy data learningrecursive program synthesis+2
15
citations
#56

A Second-Order Perspective on Model Compositionality and Incremental Learning

Angelo Porrello, Lorenzo Bonicelli, Pietro Buzzega et al.

ICLR 2025
14
citations
#57

Deep Structural Knowledge Exploitation and Synergy for Estimating Node Importance Value on Heterogeneous Information Networks

Yankai Chen, Yixiang Fang, Qiongyan Wang et al.

AAAI 2024arXiv:2402.12411
node importance estimationheterogeneous information networksgraph neural modelsstructural knowledge exploitation+3
14
citations
#58

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

Vineeth Dorna, Anmol Mekala, Wenlong Zhao et al.

NeurIPS 2025
14
citations
#59

Knowledge Editing with Dynamic Knowledge Graphs for Multi-Hop Question Answering

Yifan Lu, Yigeng Zhou, Jing Li et al.

AAAI 2025
14
citations
#60

Weak-to-Strong Generalization Through the Data-Centric Lens

Changho Shin, John Cooper, Frederic Sala

ICLR 2025
14
citations
#61

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

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

ICLR 2024
14
citations
#62

Hebbian Learning based Orthogonal Projection for Continual Learning of Spiking Neural Networks

Mingqing Xiao, Qingyan Meng, Zongpeng Zhang et al.

ICLR 2024
13
citations
#63

Roll the dice & look before you leap: Going beyond the creative limits of next-token prediction

Vaishnavh Nagarajan, Chen Wu, Charles Ding et al.

ICML 2025
13
citations
#64

Federated Causality Learning with Explainable Adaptive Optimization

Dezhi Yang, Xintong He, Jun Wang et al.

AAAI 2024arXiv:2312.05540
federated causal discoverycausal graph learningheterogeneous datadirected acyclic graph+4
13
citations
#65

Neural Causal Abstractions

Kevin Xia, Elias Bareinboim

AAAI 2024arXiv:2401.02602
causal abstractions theorycausal inference tasksneural causal modelsrepresentation learning+4
12
citations
#66

On the hardness of learning under symmetries

Bobak Kiani, Thien Le, Hannah Lawrence et al.

ICLR 2024
12
citations
#67

Mastering Symbolic Operations: Augmenting Language Models with Compiled Neural Networks

Yixuan Weng, Minjun Zhu, Fei Xia et al.

ICLR 2024
12
citations
#68

LeanAgent: Lifelong Learning for Formal Theorem Proving

Adarsh Kumarappan, Mohit Tiwari, Peiyang Song et al.

ICLR 2025
12
citations
#69

The Illusion of Unlearning: The Unstable Nature of Machine Unlearning in Text-to-Image Diffusion Models

Naveen George, Karthik Nandan Dasaraju, Rutheesh Reddy Chittepu et al.

CVPR 2025
12
citations
#70

Dynamic Sub-graph Distillation for Robust Semi-supervised Continual Learning

Yan Fan, Yu Wang, Pengfei Zhu et al.

AAAI 2024arXiv:2312.16409
semi-supervised continual learningknowledge distillationdynamic graph constructioncatastrophic forgetting+2
11
citations
#71

MetaRLEC: Meta-Reinforcement Learning for Discovery of Brain Effective Connectivity

Zuozhen Zhang, Junzhong Ji, Jinduo Liu

AAAI 2024
11
citations
#72

SHERL: Synthesizing High Accuracy and Efficient Memory for Resource-Limited Transfer Learning

Haiwen Diao, Bo Wan, XU JIA et al.

ECCV 2024arXiv:2407.07523
parameter-efficient transfer learningmemory-efficient transfer learningvision-and-language taskslanguage-only tasks+3
11
citations
#73

Precise Localization of Memories: A Fine-grained Neuron-level Knowledge Editing Technique for LLMs

Haowen Pan, Xiaozhi Wang, Yixin Cao et al.

ICLR 2025
11
citations
#74

Skill Expansion and Composition in Parameter Space

Tenglong Liu, Jianxiong Li, Yinan Zheng et al.

ICLR 2025
11
citations
#75

Knowledge-Aware Parameter Coaching for Personalized Federated Learning

Mingjian Zhi, Yuanguo Bi, Wenchao Xu et al.

AAAI 2024
11
citations
#76

Learning to Compose: Improving Object Centric Learning by Injecting Compositionality

Whie Jung, Jaehoon Yoo, Sungjin Ahn et al.

ICLR 2024
10
citations
#77

Learning Over Molecular Conformer Ensembles: Datasets and Benchmarks

Yanqiao Zhu, Jeehyun Hwang, Keir Adams et al.

ICLR 2024
10
citations
#78

Efficiently Parameterized Neural Metriplectic Systems

Anthony Gruber, Kookjin Lee, Haksoo Lim et al.

ICLR 2025
10
citations
#79

Understanding and Improving Optimization in Predictive Coding Networks

Nicholas Alonso, Jeffrey Krichmar, Emre Neftci

AAAI 2024arXiv:2305.13562
predictive coding networksinference learning algorithmbiological plausibilityoptimization methods+3
10
citations
#80

Neural Exploratory Landscape Analysis for Meta-Black-Box-Optimization

Zeyuan Ma, Jiacheng Chen, Hongshu Guo et al.

ICLR 2025arXiv:2408.10672
meta-black-box optimizationexploratory landscape analysisattention-based neural networkmulti-task neuroevolution+3
10
citations
#81

PMT: Progressive Mean Teacher via Exploring Temporal Consistency for Semi-Supervised Medical Image Segmentation

Ning Gao, Sanping Zhou, Le Wang et al.

ECCV 2024
10
citations
#82

Scalable and Certifiable Graph Unlearning: Overcoming the Approximation Error Barrier

Lu Yi, Zhewei Wei

ICLR 2025
10
citations
#83

Adaptive Self-improvement LLM Agentic System for ML Library Development

Genghan Zhang, Weixin Liang, Olivia Hsu et al.

ICML 2025
10
citations
#84

Memory-Scalable and Simplified Functional Map Learning

Robin Magnet, Maks Ovsjanikov

CVPR 2024
9
citations
#85

Epitopological learning and Cannistraci-Hebb network shape intelligence brain-inspired theory for ultra-sparse advantage in deep learning

Yingtao Zhang, Jialin Zhao, Wenjing Wu et al.

ICLR 2024
9
citations
#86

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

Lai Wei, Yuting Li, Chen Wang et al.

NeurIPS 2025
9
citations
#87

Diffusion Transformers as Open-World Spatiotemporal Foundation Models

Yuan Yuan, Chonghua Han, Jingtao Ding et al.

NeurIPS 2025
9
citations
#88

Strategy Coopetition Explains the Emergence and Transience of In-Context Learning

Aaditya Singh, Ted Moskovitz, Sara Dragutinović et al.

ICML 2025
9
citations
#89

Self-Improving Language Models for Evolutionary Program Synthesis: A Case Study on ARC-AGI

Julien Pourcel, Cédric Colas, Pierre-Yves Oudeyer

ICML 2025
9
citations
#90

Nested Learning: The Illusion of Deep Learning Architectures

Ali Behrouz, Meisam Razaviyayn, Peilin Zhong et al.

NeurIPS 2025
9
citations
#91

Improved Active Learning via Dependent Leverage Score Sampling

Atsushi Shimizu, Xiaoou Cheng, Christopher Musco et al.

ICLR 2024
9
citations
#92

Unlocking the Power of Function Vectors for Characterizing and Mitigating Catastrophic Forgetting in Continual Instruction Tuning

Gangwei Jiang, caigao jiang, Zhaoyi Li et al.

ICLR 2025
8
citations
#93

Anytime Continual Learning for Open Vocabulary Classification

Zhen Zhu, Yiming Gong, Derek Hoiem

ECCV 2024
8
citations
#94

Knowledge Graph Finetuning Enhances Knowledge Manipulation in Large Language Models

Hanzhu Chen, Xu Shen, Jie Wang et al.

ICLR 2025
8
citations
#95

Sample complexity of data-driven tuning of model hyperparameters in neural networks with structured parameter-dependent dual function

Maria-Florina Balcan, Anh Nguyen, Dravyansh Sharma

NeurIPS 2025
8
citations
#96

Adaptive Learn-then-Test: Statistically Valid and Efficient Hyperparameter Selection

Matteo Zecchin, Sangwoo Park, Osvaldo Simeone

ICML 2025
8
citations
#97

A Meta-Learning Approach to Bayesian Causal Discovery

Anish Dhir, Matthew Ashman, James Requeima et al.

ICLR 2025
8
citations
#98

MalCL: Leveraging GAN-Based Generative Replay to Combat Catastrophic Forgetting in Malware Classification

Jimin Park, AHyun Ji, Minji Park et al.

AAAI 2025
8
citations
#99

MLLM as Retriever: Interactively Learning Multimodal Retrieval for Embodied Agents

Junpeng Yue, Xinrun Xu, Börje F. Karlsson et al.

ICLR 2025
8
citations
#100

LoTUS: Large-Scale Machine Unlearning with a Taste of Uncertainty

Christoforos N. Spartalis, Theodoros Semertzidis, Efstratios Gavves et al.

CVPR 2025arXiv:2503.18314
machine unlearninginformation-theoretic boundprediction probability smoothingtransformer models+3
8
citations