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. STRATA: Reinforcement-driven Active Sampling with Tri-paradigm Adaptation for Efficient 3D Spatial Transcriptomics

    Oct 29, 2026Junchao Zhu, Ruining Deng, Chongyu Qu +7Spatial TranscriptomicsSpatial Gene Expression Prediction

    Vanderbilt University, Tennessee, USA · Weill Cornell Medicine, New York, USA · Vanderbilt University Medical Center, Tennessee, USA

  2. Robust Active Learning for More Efficient and Reliable Paths to Optimal Design

    Oct 28, 2026Hayriye Pehlivan Solak, Francesco Di Fiore, Jeroen Wackers +4Active LearningMulti-Fidelity Optimization

    Brahmal Institute for Sustainable Aviation, Imperial College London, United Kingdom. · Department of Aeronautics, Imperial College London, United Kingdom. · LHEEA Lab, Centrale Nantes / CNRS UMR 6598, Nantes, France. +1

  3. When Should We Intervene at Test Time?

    Oct 27, 2026Jiahao Zhang, Xinling Wen, Liangliang Li +1Inference-Time InterventionTest-Time Adaptation

    Zhengzhou University of Aeronautics · Xi’an University of Technology

  4. When Can a Learned Design Surrogate Be Trusted in a Self-Driving Microfluidics Laboratory? An Offline Closed-Loop Framework Built and Tested on Six Public Tables

    Oct 26, 2026Zhiyuan ZhangAutonomous ExperimentationSurrogate Modeling

    Independent research.

  5. Active Learning of Conditional Generative Models via the Transport Neural Tangent Kernel

    Oct 26, 2026Jayoung Ryu, Kyunghyun Cho, Romain LopezActive LearningNeural Tangent Kernel

    Department of Computer Science, Courant Institute School of Mathematics, Computing, and Data Science, New York University · Department of Biology, New York University

  6. Query Complexity of Learning Axis-Aligned Partitions

    Oct 26, 2026Hadley Black, Arya Mazumdar, Barna Saha +1Query ComplexityActive Learning

    Baruch College, CUNY. · UC San Diego. · ETH Zürich.

  7. Should Pseudo-Labels Share Mini-Batches with Labeled Examples? Semi-Supervised Continual Active Learning with Limited Training Cost

    Oct 26, 2026Shiqi Zhang, Tuomas VirtanenActive LearningPseudo-Labeling

    Faculty of Information Technology and Communication Sciences Tampere University, Tampere, Finland

  8. Geometric Consistency Based Label-Free Validation for Checkpoint Selection in Audio Active Learning

    Oct 26, 2026Shiqi Zhang, Tuomas VirtanenActive LearningAudio Classification

    Faculty of Information Technology and Communication Sciences, Tampere University, Tampere, Finland

  9. An actively trained neural operator for near-explicit atmospheric chemistry

    Oct 24, 2026Zhi-Song Liu, Wenqing Peng, Ammar Kheder +2Neural Surrogate ModelingFourier Neural Operator

    Department of Computational Engineering, LUT University, Finland. · Atmospheric Modelling Center, Lahti (AMC-Lahti), Finland. · Institute for Atmospheric and Earth System Research (INAR), University of Helsinki, Finland. +1

  10. Asking Less, Adapting Better: Feedback-Efficient Test-Time Adaptation for Vision-and-Language Navigation

    Oct 22, 2026Zixu Wang, Huaquan Zhang, Shoukai Xu +3Vision-Language NavigationContinual Test-Time Adaptation

    School of Software Engineering, South China University of Technology, Guangzhou, China · Institute for Super Robotics (Huangpu), Guangzhou, China · Key Laboratory of Big Data and Intelligent Robot, Ministry of Education, Guangzhou 510006, China

  11. Hidden Cartographer: Hidden State Guided Data Selection for Dual Budgeted Instruction Tuning

    Oct 18, 2026Zixuan Qin, Qi Qin, Erbo Li +3Training Data SelectionInstruction-Tuning Data Selection

    Center for Applied Statistics, School of Statistics, Renmin University of China · Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing

  12. HSPR: Recovering Software-Agent Benchmark Scores via Hierarchical Posterior Inference

    Oct 17, 2026Wanyi Chen, Wanqin Shen, Yuanchen Shi +2AI Agent EvaluationActive Learning

    Soochow University · Singapore Management University

  13. PAC Learning with Query Feedback

    Oct 16, 2026Chase Hutton, Adam Melrod, Han ShaoPAC LearningMulticlass Classification

    University of Maryland · Harvard University

  14. Deconstructing Multi-Task Active Learning: The Paradox of Gradient Conflict and Orthogonal Decomposition

    Oct 16, 2026Juho Jung, Seongjae Kang, Jinyoung HanActive LearningMulti-Task Learning

    Sungkyunkwan University · KAIST

  15. Towards optimal selection schedules for online active learning

    Oct 16, 2026Hugo Cui, Francesca Mignacco, Francesco MoriActive LearningLinear Classification

    Université Paris-Saclay, CNRS, Laboratoire de mathématiques d’Orsay, 91405, Orsay, France · Joseph Henry Laboratories of Physics and Lewis–Sigler Institute, Princeton University, Princeton NJ 08544, USA · Initiative for the Theoretical Sciences, The Graduate Center, City University of New York, 365 Fifth Ave, New York NY 10016, USA +1

  16. Edit Discovery in Human-AI Interactions

    Oct 15, 2026Alireza Mirrokni, Shayan Kiyani, George Pappas +1Human-in-the-Loop EvaluationHuman-AI Interaction

    EPFL · University of Pennsylvania

  17. Beyond Fixed Acquisition Functions: Temporal Difference Active Learning for Perturbation Discovery

    Oct 15, 2026Xudong Zhang, Jianzhe Li, Yitong Tang +1Active LearningAdaptive Sampling

    Center for Machine Learning Research, Peking University, Beijing, China · AI for Science Institute (AISI), Beijing, China

  18. Pixels to Tokens: Token Space Efficient Active Learning for Low-Budget Semantic Segmentation

    Oct 14, 2026Utku Cicek, Mahip Singh, Ziyao Shang +5Active Learning

    University of Waterloo · Apple

  19. From Human Corrections to Learned Segmentations: A Critical Mathematical Review of Information, Learning, and Human Effort

    Oct 14, 2026Jon SporringHuman-in-the-Loop AIHuman-in-the-Loop Annotation

    Department of Computer Science, University of Copenhagen, DK-2100 Copenhagen, Denmark

  20. Improving Category-Aware Active Domain Adaptation via Uncertainty-Guided Region Coverage

    Oct 14, 2026My Tra Nguyen Huynh, Viet Cuong TaDomain AdaptationActive Learning

    VNU University of Engineering and Technology, Hanoi, 100000, Vietnam.

  21. ActMOF: Mapping Reticular Synthesis through Active Learning

    Oct 14, 2026Hongrui Sheng, Shutian Liang, Reid A. Coyle +5Active LearningMaterials Science

    Department of Chemistry, Washington University, St. Louis, Missouri 63130, United States · Department of Chemistry, Fudan University, Shanghai 200438, China · Department of Energy, Environmental and Chemical Engineering, Washington University, St. Louis, Missouri 63130, United States +2

  22. Autonomous Science Bench: Evaluating AI Agents for Autonomous Scientific Discovery

    Oct 13, 2026Yibo Wen, Han LiuAutonomous Scientific DiscoveryScientific Agent Benchmarks

    Northwestern University

  23. SPARCL: Spatially Adaptive Regional Coverage for Active Learning in Chest X-ray Analysis

    Oct 13, 2026Juho Jung, Seongjae Kang, Mijoo Kim +4Active LearningMedical Image Segmentation

    VUNO Inc., Seoul, South Korea

  24. CÆNL: Collapse-Based Active Neural Learning with Objective-Aligned Representation Control

    Oct 13, 2026Saad AlqithamiActive LearningRepresentation Learning

  25. Boosting the Learning for Ranking Patterns

    Oct 12, 2026Nassim Belmecheri, Noureddine Aribi, Nadjib Lazaar +2Learning to RankUser Preference Modeling

    Lab. LITIO, Universit´e Oran1, 31000, Oran, Algeria. · LIRMM, Universit´e de Montpellier, CNRS, 34000, Montpellier, France. · TASC (LS2N-CNRS), IMT Atlantique, 44307, Nantes, France.

  26. Active Learning for Finding a Needle in a Haystack

    Oct 10, 2026Emily Silcock, Simon LöweSubgroup RobustnessActive Learning

    Harvard University · Burning Glass Institute

  27. Agent-Guided Evidence Acquisition for Emotion-Cause Pair Extraction

    Oct 10, 2026Zhuangzhuang Pan, Yan Xia, Chee Seng ChanEvidence SelectionRelation Extraction

    Universiti Malaya, Malaysia · Suzhou University of Technology, China · VinUniversity, Vietnam

  28. SynAct: Synergistic Active Feedback Learning for LLM Agents

    Oct 8, 2026Ning Liu, Ian Li, Kristina KlinknerLLM Agent TrainingActive Learning

    Amazon

  29. Exploiting Gradients in Bayesian Inference of Expensive Simulators

    Oct 8, 2026Šimon Soldát, Václav ŠmídlSimulation-Based InferenceBayesian Optimization

    Department of Computer Science, Faculty of Electrical Engineering, Czech Technical University in Prague, Czech Republic · Institute of Plasma Physics of the Czech Academy of Sciences, Prague, Czech Republic

  30. EmbodiedRSI: Active Continual Robot Learning Through Hypothesis-Guided Co-Evolution

    Oct 7, 2026Python Song, Zhixuan Liang, Kelsey Fu +3Continual Robot LearningRobot Skill Learning

    Columbia University · Princeton University