SOTAVerified

Active Learning

Active Learning is a paradigm in supervised machine learning which uses fewer training examples to achieve better optimization by iteratively training a predictor, and using the predictor in each iteration to choose the training examples which will increase its chances of finding better configurations and at the same time improving the accuracy of the prediction model

Source: Polystore++: Accelerated Polystore System for Heterogeneous Workloads

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 51–75 of 3073 papers

TitleStatusHype
Enhancing Treatment Effect Estimation via Active Learning: A Counterfactual Covering PerspectiveCode0
Probabilistic Embeddings for Frozen Vision-Language Models: Uncertainty Quantification with Gaussian Process Latent Variable ModelsCode0
Balancing Accuracy, Calibration, and Efficiency in Active Learning with Vision Transformers Under Label Noise—0
Label-efficient Single Photon Images Classification via Active Learning—0
RAFT: Robust Augmentation of FeaTures for Image Segmentation—0
AnomalyMatch: Discovering Rare Objects of Interest with Semi-supervised and Active LearningCode0
The Search for Squawk: Agile Modeling in Bioacoustics—0
Sailing AI by the Stars: A Survey of Learning from Rewards in Post-Training and Test-Time Scaling of Large Language ModelsCode2
TActiLE: Tiny Active LEarning for wearable devices—0
Reduced-order structure-property linkages for stochastic metamaterials—0
Inconsistency-based Active Learning for LiDAR Object Detection—0
HeAL3D: Heuristical-enhanced Active Learning for 3D Object Detection—0
Subspace-Distance-Enabled Active Learning for Efficient Data-Driven Model Reduction of Parametric Dynamical Systems—0
Curiosity Driven Exploration to Optimize Structure-Property Learning in MicroscopyCode0
Context Selection and Rewriting for Video-based Educational Question GenerationCode0
Geometry-aware Active Learning of Spatiotemporal Dynamic Systems—0
Performance of Machine Learning Classifiers for Anomaly Detection in Cyber Security ApplicationsCode0
CHASe: Client Heterogeneity-Aware Data Selection for Effective Federated Active Learning—0
Compositional Active Learning of Synchronizing Systems through Automated Alphabet Refinement—0
From Reviews to Dialogues: Active Synthesis for Zero-Shot LLM-based Conversational Recommender System—0
Simulating Before Planning: Constructing Intrinsic User World Model for User-Tailored Dialogue Policy Planning—0
Parsimonious Dataset Construction for Laparoscopic Cholecystectomy Structure Segmentation—0
Uncertainty Quantification in Graph Neural Networks with Shallow Ensembles—0
Efficient Process Reward Model Training via Active LearningCode1
Scholar Inbox: Personalized Paper Recommendations for Scientists—0
Show:102550
← PrevPage 3 of 123Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1TypiClustAccuracy93.2—Unverified
2PT4ALAccuracy93.1—Unverified
3Learning lossAccuracy91.01—Unverified
4CoreGCNAccuracy90.7—Unverified
5Core-setAccuracy89.92—Unverified
6Random Baseline (Resnet18)Accuracy88.45—Unverified
7Random Baseline (VGG16)Accuracy85.09—Unverified