Active Learning

Ask about this topic

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

296 papers39 papers in the last four weeks, up 22% on the four weeks before. 0.2% of all new papers.

  1. Learning U-Statistics with Active Inference

    May 12, 2026Xiaoning Wang, Yuyang Huo, Liuhua Peng +1Active InferenceU-Statistics

    School of Statistics and Data Sciences, LPMC, KLM-DASR and LEBPS, Nankai University, Tianjin, China · School of Mathematics and Statistics, The University of Melbourne, Melbourne, Australia

  2. MASS-DPO: Multi-negative Active Sample Selection for Direct Policy Optimization

    May 11, 2026Rohan Surana, Xintong Li, Sheldon Yu +7Direct Preference OptimizationActive Learning

    1UC San Diego · 2Adobe Research

  3. Active Learning for Gaussian Process Regression Under Self-Induced Boltzmann Weights

    May 11, 2026Jixiang Qing, Henry Moss, Matthias SachsActive LearningGaussian Process Regression

    MARS: Mathematics for AI in Real-world Systems, School of Mathematical Sciences, Lancaster University, Lancaster, LA1 4YF, United Kingdom.

  4. Portable Active Learning for Object Detection

    May 11, 2026Rashi Sharma, Justin Timothy C. Bersamin, Karthikk SubramanianActive LearningUncertainty Sampling

    Panasonic R&D Center Singapore · Nanyang Technological University

  5. Active-SAOOD: Active Sparsely Annotated Oriented Object Detection in Remote Sensing Images

    May 11, 2026Yu Lin, Jianghang Lin, Kai Ye +2Remote Sensing Image UnderstandingActive Learning

    Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, 361005, P.R. China.

  6. Clip-level Uncertainty and Temporal-aware Active Learning for End-to-End Multi-Object Tracking

    May 11, 2026Riku Inoue, Shogo Sato, Kazuhiko Murasaki +3Active LearningUncertainty Sampling

    NTT, Inc., Kanagawa, Japan

  7. SMT-Based Active Learning of Weighted Automata

    May 8, 2026Tiago Ferreira, Kevin Batz, Alexandra SilvaActive LearningSatisfiability Modulo Theories

    University College London, London, UK · Cornell University, Ithaca, NY, USA

  8. Physics-based Digital Twins for Integrated Thermal Energy Systems Using Active Learning

    May 7, 2026Umme Mahbuba Nabila, Paul Seurin, Linyu Lin +1Surrogate ModelingSparse Identification of Nonlinear Dynamics

    Department of Nuclear Engineering and Radiological Sciences, University of Michigan, Ann Arbor, MI 48109, United States · Nuclear Science & Technology Division, Idaho National Laboratory, Idaho Falls, ID 83415, United States · Department of Computer Science and Engineering, University of Michigan, Ann Arbor, MI 48109, United States

  9. Decoupled PFNs: Identifiable Epistemic-Aleatoric Decomposition via Structured Synthetic Priors

    May 7, 2026Richard Bergna, Stefan Depeweg, José Miguel Hernández-LobatoUncertainty QuantificationBayesian Optimization

    University of Cambridge · 2Siemens AG

  10. Active Learning for Communication Structure Optimization in LLM-Based Multi-Agent Systems

    May 7, 2026Huchen Yang, Xinghao Dong, Dan Negrut +1Multi-Agent LLM SystemsMulti-Agent System Optimization

    University of Wisconsin–Madison

  11. Non-Myopic Active Feature Acquisition via Pathwise Policy Gradients

    May 6, 2026Linus Aronsson, Morteza Haghir ChehreghaniPolicy GradientActive Learning

    Department of Computer Science and Engineering · Chalmers University of Technology & University of Gothenburg · Gothenburg, Sweden

  12. SPADE: Faster Drug Discovery by Learning from Sparse Data

    May 6, 2026Rahul Nandakumar, Ben Fauber, Deepayan ChakrabartiMolecular OptimizationAI-Assisted Scientific Research

    McCombs School of Business University of Texas at Austin Austin, TX · NVIDIA

  13. Pretrained Model Representations as Acquisition Signals for Active Learning of MLIPs

    May 5, 2026Eszter Varga-Umbrich, Shikha Surana, Paul Duckworth +3Machine Learning Interatomic PotentialsActive Learning

    1InstaDeep · University of Cambridge

  14. Selective Prediction from Agreement: A Lipschitz-Consistent Version Space Approach

    May 4, 2026Mohamadsadegh KhosravaniSelective PredictionActive Learning

    University of Regina

  15. Gradient-Discrepancy Acquisition for Pool-Based Active Learning

    May 4, 2026Mohamadsadegh Khosravani, Sandra ZillesActive Learning

    Department of Computer Science University of Regina · University of Regina

  16. Active multiple matrix completion with adaptive confidence sets

    May 4, 2026Andrea Locatelli, Alexandra Carpentier, Michal ValkoActive LearningMulti-Task Learning

    OvGU Magdeburg · SequeL team, Inria Lille

  17. Exploring Entropy-based Active Learning for Fair Brain Segmentation

    May 3, 2026Ghazal Danaee, Mélanie Gaillochet, Christian Desrosiers +2Active LearningGroup Fairness

    École de technologie supérieure, Montréal, QC, Canada · Polytechnique Montréal, Montréal, QC, Canada · Mila - Quebec AI Institute, Montréal, QC, Canada

  18. IMPACT-Scribe: Interactive Temporal Action Segmentation with Boundary Scribbles and Query Planning

    May 3, 2026Qian Yin, Di Wen, Kunyu Peng +11Temporal Action SegmentationHuman-in-the-Loop Annotation

    Karlsruhe Institute of Technology, 76131 Karlsruhe, Germany · INSAIT, Sofia University “St. Kliment Ohridski”, 1784 Sofia, Bulgaria · ETH Zurich, 8092 Zurich, Switzerland +1

  19. Leveraging Vision-Language Models as Weak Annotators in Active Learning

    May 1, 2026Phuong Ngoc Nguyen, Kaito Shiku, Ryoma Bise +2Vision-Language ModelsActive Learning

    Kyushu University, Japan.

  20. Rendering-Aware Sparse Sampling for BRDF Acquisition

    Apr 29, 2026W. Cao, D. Jönsson, Z. Huang +1Active LearningPhysically Based Rendering

    Media and Information Technology, Department of Science and Technology, Linköping University, SE-601 74 Norrköping, Sweden

  21. Learning to Think from Multiple Thinkers

    Apr 27, 2026Nirmit Joshi, Roey Magen, Nathan Srebro +2CoT SupervisionActive Learning

    Toyota Technological Institute at Chicago. · Weizmann Institute of Science. · New York University.

  22. Accelerating Quantum Materials Characterization: Hybrid Active Learning for Autonomous Spin Wave Spectroscopy

    Apr 26, 2026William RatcliffActive LearningMaterials Science

    NIST Center for Neutron Research, National Institute of Standards and Technology, Gaithersburg, MD 20899, USA

  23. An Analysis of Active Learning Algorithms using Real-World Crowd-sourced Text Annotations

    Apr 25, 2026Varun Totakura, Ankita Singh, Yushun Dong +1Human-in-the-Loop AnnotationActive Learning

    Department of Computer Science Florida State University Tallahassee, FL, USA

  24. ProEval: Proactive Failure Discovery and Efficient Performance Estimation for Generative AI Evaluation

    Apr 25, 2026Yizheng Huang, Wenjun Zeng, Aditi Kumaresan +1Active LearningAI Safety Evaluation

    Google DeepMind

  25. Hard to See, Hard to Label: Generative and Symbolic Acquisition for Subtle Visual Phenomena

    Apr 24, 2026Renjith Prasad, Rishabh Sharma, Andrew E. Shao +8Industrial Anomaly DetectionActive Learning

    University of South Carolina · AI Research Lab, HPE Labs, Hewlett Packard Enterprise · Indian AI Research Organization +1

  26. Autonomous Reliability Qualification of Ga2_2O3_3-based Hydrogen and Temperature Sensors via Safe Active Learning

    Apr 22, 2026Davi Febba, William A. Callahan, Anna Sacchi +1Active LearningAutonomous Experimentation

    Materials Science Center, National Laboratory of the Rockies (NLR), Golden, CO 80401, USA

  27. Energy-Based Open-Set Active Learning for Object Classification

    Apr 22, 2026Zongyao Lyu, William J. BeksiActive LearningOpen-Set Recognition

    The University of Texas at Arlington, Arlington TX 76019, USA

  28. RareSpot+: A Benchmark, Model, and Active Learning Framework for Small and Rare Wildlife in Aerial Imagery

    Apr 21, 2026Bowen Zhang, Jesse T. Boulerice, Charvi Mendiratta +4Remote Sensing Small Object DetectionSmall Object Detection

    University of California, Santa Barbara, 93106, California, United States of America. · 2Smithsonian National Zoo and Conservation Biology Institute, 20008, Washington, DC, United States of America. · 3Stanford University, 94305, California, United States of America. +1

  29. When Active Learning Falls Short: An Empirical Study on Chemical Reaction Extraction

    Apr 21, 2026Simin Yu, Sufia FathimaDocument Information ExtractionActive Learning

    Data and Knowledge Engineering

  30. Human-Machine Co-Boosted Bug Report Identification with Mutualistic Neural Active Learning

    Apr 20, 2026Guoming Long, Shihai Wang, Hui Fang +1Human-in-the-Loop AnnotationActive Learning

    University of Electronic Science and Technology of China, Chengdu, China · Loughborough University, Loughborough, United Kingdom · IDEAS Lab, University of Birmingham, Birmingham, United Kingdom