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 71–80 of 3569 papers

TitleStatusHype
Fast Rate Bounds for Multi-Task and Meta-Learning with Different Sample Sizes—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
MetaUAS: Universal Anomaly Segmentation with One-Prompt Meta-LearningCode2
Meta-learning Slice-to-Volume Reconstruction in Fetal Brain MRI using Implicit Neural Representations—0
DyGSSM: Multi-view Dynamic Graph Embeddings with State Space Model Gradient Update—0
Towards Adaptive Meta-Gradient Adversarial Examples for Visual TrackingCode0
Modeling Unseen Environments with Language-guided Composable Causal Components in Reinforcement Learning—0
Show:102550
← PrevPage 8 of 357Next →
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