Overview

Active learning studies how to choose data or queries so models can learn effectively with fewer labels, measurements, or experiments. Common approaches include uncertainty sampling, diversity and coreset selection, Bayesian information gain, batch strategies, and cost-aware or human-in-the-loop querying; scientific applications also use Gaussian processes, multi-fidelity models, and physics-based acquisition to guide simulations and laboratory work. Work spans image and language benchmarks, medical annotation, robotics, and scientific discovery, with newer methods using foundation-model representations and adapting selection to class imbalance, domain shift, or label noise. A central open tension is that no acquisition strategy wins everywhere: gains depend on the task, budget, model and data, and random sampling can match or outperform sophisticated methods, making realistic evaluations and strong baselines essential.

Latest papers

CardsList

330 papers35 papers in the last four weeks, down 26% on the four weeks before. 0.3% of all new papers.

  1. Sample-efficient end-to-end Optical Music Recognition through Active Learning

    Nov 19, 2026Eric Ayllon, Francisco J. Castellanos, Antonio Rios-VilaOptical Music RecognitionData-Efficient Learning

  2. Enhancing Active Learning Performance with Initial Data Selection Based on Foundation Models

    Nov 18, 2026Mohammad Mirzaee, Mehrshad Fallah Estalkhzir, Mohammad Reza MohammadiActive LearningObject Detection

  3. Fill-Distance-Guided Active Learning for Causal Function Recovery under Network Interference

    Nov 18, 2026Peiyao Liu, Hongtao Zhu, Sizhe Zhang +3Causal InferenceCausal Effect Estimation

  4. Improved Leverage Score Sampling for Constrained Active Linear Regression

    Nov 18, 2026Aarshvi Gajjar, Syamantak Kumar, Aditya Makkar +2Active LearningLinear Regression

  5. Risk-optimal active learning with informative abstention

    Nov 18, 2026Fariborz Setoudehtazangi, Geoffrey J. McLachlanActive LearningStatistical Learning Theory

  6. Prioritize, Don't Decide: What We Learned Auditing a Deployed Human-in-the-Loop CV Sorter

    Nov 17, 2026Hadi Mohammadi, Jeroen Sparla, Alexandros Paliouras +2Human-in-the-Loop EvaluationLearning to Rank

  7. Asking the right question is key to AI discovery in a chain of hypotheses

    Nov 15, 2026Hu CangAutonomous Scientific DiscoveryLarge Language Model-Guided Scientific Discovery

  8. Interactive Program Induction with Language Model Priors

    Nov 13, 2026Robin Shing Moon Chan, Ryan CotterellInductive InferenceActive Learning

  9. Sample-efficient prediction of high-entropy alloy strength through outcome-aware robust sequential learning

    Nov 13, 2026Ahmed Shoyeb Raihan, Md Habibor Rahman, Ashish Nimbarte +1Materials Property PredictionActive Learning

  10. Systematic Evaluation of Training Data Generation Strategies for Machine Learning-Based Molecular and Materials Property Prediction

    Nov 12, 2026Minh Nghia Nguyen, Beate Paulus, Akhil S. NairTraining Data SelectionActive Learning

  11. Fermat ProbCover: Coverage-Based Active Learning on Fermat Distance Graphs

    Nov 10, 2026Gokul Bhusal, Delanna Do, Kevin Miller +2Active Learning

  12. Building heterogeneous multistep workflows in automated microscopy: reward design and knowledge transfer for autonomous structure property discovery

    Nov 8, 2026Sergei V. KalininAutonomous ExperimentationScientific Workflow Automation

  13. TALK: One-Shot Batch Design for Protein Variant Effect Prediction

    Nov 8, 2026Qiao Huang, Ao Shen, Jie Du +1Protein Mutation Effect PredictionProtein Fitness Prediction

  14. Generative Active Learning for Label-Efficient Pan-Organ Ultrasound Diagnosis

    Nov 6, 2026Yaofei Duan, Yuhao Huang, Yuan Gao +9Active LearningUltrasound Image Classification

  15. Active Learning of Robust Models

    Nov 6, 2026Mizu Nishikawa-Toomey, Andreas Kirsch, Laurent Charlin +1Active LearningDistribution Shift Robustness

  16. k-Volume: a Unified Active Learning Strategy

    Nov 6, 2026Eliot Tron, Alain Celisse, Christophe Denis +1Active LearningDiversity-Aware Sampling

  17. When, Where, How: Active In-Context Learning for Tabular Foundation Models

    Nov 5, 2026Christian M. M. FreyActive LearningIn-Context Learning

  18. KolTa: A Physics-Informed Active Learning Framework for Formulation Discovery with Limited Data

    Nov 4, 2026Boyong Tang, Lei Yang, Tao WangActive LearningPhysics-Informed ML

  19. ARIDA - Active railway infrastructure dataset annotation using neural network predictions

    Nov 3, 2026Maximilian Dornik, Christian Sieberichs, Simon Geerkens +1Automated Data AnnotationHuman-in-the-Loop Annotation

  20. Forgetting to Improve: Principled Data Removal in Active Learning

    Nov 2, 2026Manuel Wendl, Erik Englesson, Andreas Krause +1Active LearningDataset Pruning

  21. Anomaly-ranked confirmation slows new-class learning

    Nov 2, 2026Argyro Sasli, Michael CoughlinActive LearningAnomaly Detection

  22. Inner optimizers in active-learning Kriging reliability analysis: a pre-specified comparison and the unconservative estimates left by unlearned failure modes

    Nov 2, 2026Wei-Chang YehActive LearningSurrogate-Assisted Optimization

  23. End-to-End Stability of Online Active Learning in Large-Scale Neural Systems

    Nov 2, 2026Shuiwen Shen, Jinhua Zhang, Chenlei Hou +6Online LearningActive Learning

  24. Does reflective LLM feedback survive a wet-lab-scale label budget?

    Nov 1, 2026Haoxuan Zeng, Xin LuoLLM Self-RefinementActive Learning

  25. Online Active Learning Architecture for Safety-Critical Control Systems

    Nov 1, 2026Shuiwen Shen, Jinhua Zhang, Yan Wang +5Active LearningNeural Network Control

  26. Resolve, Clear, or Defer: Training-Free Active Prototype Triage for Ecological Detection Pipelines

    Nov 1, 2026Anirudh Potlapally, Brijesh Nanda Brunda Yogananda, Jianyang Gu +4Active LearningPrototype-Based Classification

  27. HALO: Hierarchical Evidence Selection and Reinforcement Learning for Allocating Budgeted Label Optimization from Longitudinal Clinical Records

    Oct 31, 2026Huaiyuan Ying, Feiqing Huang, Ryumei Nakada +2Active LearningReinforcement Learning

  28. Spatial Uncertainty Analytics for Budget-Limited Inspection of Hyperspectral Scenes

    Oct 31, 2026Ritesh Sharma, Yuichi MotaiUncertainty SamplingActive Learning

  29. DEPLOY-RL: Active Boundary Discovery and Conservative Certification for Deployable Reinforcement Learning in Safety-Critical Continuous Processes

    Oct 30, 2026Yeojin Jang, Minu Baek, Gihun Gil +8Safe RLActive Learning