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 21–30 of 3569 papers

TitleStatusHype
Online Adaptation of Language Models with a Memory of Amortized ContextsCode2
VRP-SAM: SAM with Visual Reference PromptCode2
Learning a Decision Tree Algorithm with TransformersCode2
Learning Universal PredictorsCode2
Fine-Grained Prototypes Distillation for Few-Shot Object DetectionCode2
XLand-MiniGrid: Scalable Meta-Reinforcement Learning Environments in JAXCode2
JaxMARL: Multi-Agent RL Environments and Algorithms in JAXCode2
A physics-informed and attention-based graph learning approach for regional electric vehicle charging demand predictionCode2
MetaPortrait: Identity-Preserving Talking Head Generation with Fast Personalized AdaptationCode2
Transformers learn in-context by gradient descentCode2
Show:102550
← PrevPage 3 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