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 1251–1300 of 3569 papers

TitleStatusHype
Contrastive Meta-Learning for Few-shot Node ClassificationCode0
Generalizing Reward Modeling for Out-of-Distribution Preference LearningCode0
CMML: Contextual Modulation Meta Learning for Cold-Start RecommendationCode0
General-Purpose In-Context Learning by Meta-Learning TransformersCode0
An Ensemble of Epoch-wise Empirical Bayes for Few-shot LearningCode0
Learning advisor networks for noisy image classificationCode0
Latent-Optimized Adversarial Neural Transfer for Sarcasm DetectionCode0
Latent Bottlenecked Attentive Neural ProcessesCode0
Latent Representation Learning of Multi-scale Thermophysics: Application to Dynamics in Shocked Porous Energetic MaterialCode0
Latent Task-Specific Graph Network SimulatorsCode0
Few-shot Conformal Prediction with Auxiliary TasksCode0
Advancing Open-Set Domain Generalization Using Evidential Bi-Level Hardest Domain SchedulerCode0
Clustering Indices based Automatic Classification Model SelectionCode0
LabelCraft: Empowering Short Video Recommendations with Automated Label CraftingCode0
Layer-compensated Pruning for Resource-constrained Convolutional Neural NetworksCode0
Few-Shot Classification of Skin Lesions from Dermoscopic Images by Meta-Learning Representative EmbeddingsCode0
Joint inference and input optimization in equilibrium networksCode0
Clustered Task-Aware Meta-Learning by Learning from Learning PathsCode0
It HAS to be Subjective: Human Annotator Simulation via Zero-shot Density EstimationCode0
Geo-ORBIT: A Federated Digital Twin Framework for Scene-Adaptive Lane Geometry DetectionCode0
Few-shot classification in Named Entity Recognition TaskCode0
Fast Few-Shot Classification by Few-Iteration Meta-LearningCode0
Closed-form Sample Probing for Learning Generative Models in Zero-shot LearningCode0
Few-Shot Character Understanding in Movies as an Assessment to Meta-Learning of Theory-of-MindCode0
Investigating Large Language Models for Complex Word Identification in Multilingual and Multidomain SetupsCode0
Is Bayesian Model-Agnostic Meta Learning Better than Model-Agnostic Meta Learning, Provably?Code0
Goal-Conditioned End-to-End Visuomotor Control for Versatile Skill PrimitivesCode0
Joint Optimization of Class-Specific Training- and Test-Time Data Augmentation in SegmentationCode0
Few-Shot Calibration of Set Predictors via Meta-Learned Cross-Validation-Based Conformal PredictionCode0
Few-shot calibration of low-cost air pollution (PM2.5) sensors using meta-learningCode0
CLID-MU: Cross-Layer Information Divergence Based Meta Update Strategy for Learning with Noisy LabelsCode0
Interpretable Meta-Measure for Model PerformanceCode0
META-Learning Eligibility Traces for More Sample Efficient Temporal Difference LearningCode0
Gradient-Based Meta-Learning with Learned Layerwise Metric and SubspaceCode0
Active exploration in parameterized reinforcement learningCode0
Interval Bound Interpolation for Few-shot Learning with Few TasksCode0
Gradient Estimators for Implicit ModelsCode0
Few-Shot Adversarial Learning of Realistic Neural Talking Head ModelsCode0
Meta-Learning for Efficient Fine-Tuning of Large Language ModelsCode0
Meta Learning for Efficient Fine-Tuning of Large Language ModelsCode0
Few-Shot Adaptive Gaze EstimationCode0
An Investigation of Few-Shot Learning in Spoken Term ClassificationCode0
Classical Sequence Match is a Competitive Few-Shot One-Class LearnerCode0
INR-Arch: A Dataflow Architecture and Compiler for Arbitrary-Order Gradient Computations in Implicit Neural Representation ProcessingCode0
Inverse Learning with Extremely Sparse Feedback for RecommendationCode0
Incremental Meta-Learning via Episodic Replay Distillation for Few-Shot Image RecognitionCode0
Incorporating Test-Time Optimization into Training with Dual Networks for Human Mesh RecoveryCode0
Incremental Few-Shot Learning with Attention Attractor NetworksCode0
Improving Meta-Learning Generalization with Activation-Based Early-StoppingCode0
A new benchmark for group distribution shifts in hand grasp regression for object manipulation. Can meta-learning raise the bar?Code0
Show:102550
← PrevPage 26 of 72Next →
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