SOTAVerified

Meta-Learning

Meta-learning is a methodology considered with "learning to learn" machine learning algorithms.

( Image credit: Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks )

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 51–75 of 3569 papers

TitleStatusHype
A Brain Graph Foundation Model: Pre-Training and Prompt-Tuning for Any Atlas and DisorderCode1
Darwin Godel Machine: Open-Ended Evolution of Self-Improving AgentsCode5
Dynamic Spectral Backpropagation for Efficient Neural Network Training—0
Meta-Learning Approaches for Speaker-Dependent Voice Fatigue Models—0
CellCLAT: Preserving Topology and Trimming Redundancy in Self-Supervised Cellular Contrastive LearningCode0
Generalizable Heuristic Generation Through Large Language Models with Meta-Optimization—0
MetaWriter: Personalized Handwritten Text Recognition Using Meta-Learned Prompt Tuning—0
MetaSTNet: Multimodal Meta-learning for Cellular Traffic Conformal Prediction—0
DreamPRM: Domain-Reweighted Process Reward Model for Multimodal Reasoning—0
MetaGMT: Improving Actionable Interpretability of Graph Multilinear Networks via Meta-Learning Filtration—0
Deciphering Trajectory-Aided LLM Reasoning: An Optimization PerspectiveCode0
MetaBox-v2: A Unified Benchmark Platform for Meta-Black-Box OptimizationCode2
Evolving Machine Learning: A Survey—0
Understanding Prompt Tuning and In-Context Learning via Meta-LearningCode0
Beyond Induction Heads: In-Context Meta Learning Induces Multi-Phase Circuit Emergence—0
Finetuning-Activated Backdoors in LLMsCode0
Meta-reinforcement learning with minimum attention—0
Meta-PerSER: Few-Shot Listener Personalized Speech Emotion Recognition via Meta-learning—0
Meta-Learning an In-Context Transformer Model of Human Higher Visual Cortex—0
Fast Rate Bounds for Multi-Task and Meta-Learning with Different Sample Sizes—0
Mitigating Spurious Correlations with Causal Logit Perturbation—0
A MIND for Reasoning: Meta-learning for In-context DeductionCode0
CLIP-aware Domain-Adaptive Super-Resolution—0
Ready2Unlearn: A Learning-Time Approach for Preparing Models with Future Unlearning Readiness—0
System Prompt Optimization with Meta-LearningCode0
Show:102550
← PrevPage 3 of 143Next →
All datasetsML10MT50ML45OMNIGLOT - 1-Shot, 20-way

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1MZ+ReconMeta-train success rate97.8—Unverified
2MZMeta-train success rate97.6—Unverified
3MAMLMeta-test success rate36—Unverified
4RL^2Meta-test success rate10—Unverified
5DnCMeta-test success rate5.4—Unverified
6PEARLMeta-test success rate0—Unverified
#ModelMetricClaimedVerifiedStatus
1SoftModuleAverage Success Rate60—Unverified
2Multi-task multi-head SACAverage Success Rate35.85—Unverified
3DisCorAverage Success Rate26—Unverified
4NDPAverage Success Rate11—Unverified
#ModelMetricClaimedVerifiedStatus
1MZ+ReconMeta-test success rate (zero-shot)18.5—Unverified
2MZMeta-test success rate (zero-shot)17.7—Unverified
#ModelMetricClaimedVerifiedStatus
1Metadrop% Test Accuracy95.75—Unverified