Latest Active Learning Research Papers

The newest Active Learning papers from across the field — arXiv, NeurIPS, CVPR, Nature, and more — refreshed daily and ranked by relevance. Distill AI tracks Active Learning so you don’t have to: get the standout work delivered to your inbox every morning, with 2-sentence summaries and the option to chat with any paper.

Recent papers

• Subspace Inference Enables Efficient Active Reward Learning from Preferences
  Yutai Zhou, Erdem Bıyık · arXiv · Sep 3, 2026

  Reinforcement learning from human feedback (RLHF) has emerged as a powerful yet sample-inefficient approach for learning reward models from human preferences, making active learning a critical component in synthesizing informative preferenc…

• LoRA-TSD: Tangent-Space Spectral Descent for LoRA via Muon-Style Updates
  Dmitrii Andriianov, Andrey Veprikov, Aleksandr Beznosikov · arXiv · Sep 2, 2026

  Low-rank adaptation (LoRA) is the standard way to fine-tune large models, yet when its two factors are trained independently, the update ignores the geometry of the low-rank weight change it induces. We introduce LoRA-TSD, an optimizer that…

• Enhancing Bayesian Optimization and Active Learning Through Kernel Diversity
  Heng Zhang, Haotian Xiang, Qin Lu, Konstantinos D. Polyzos et al. · arXiv · Aug 25, 2026

  Hyperparameter selection remains a key challenge in Bayesian optimization (BO) and Bayesian active learning (AL), as model misspecification can lead to suboptimal performance, while more accurate fully Bayesian treatments typically rely on …

• Diversity-Based Active Learning: An Evaluation of Metric Spaces for Active Learning Selection
  Siddharth Chilamkur, Dorit S. Hochbaum · arXiv · Aug 24, 2026

  With rapid advancement over the last few years, many different methods are now widely used for classification. However, training these models requires substantial labeled data. Active Learning is a potential solution to this problem. Pool-b…

• On the Fragility of Self-Improving Agents: Variance, Task Order, and Underspecification
  Qinyuan Ye, Yu Li, Yada Pruksachatkun, Jiaxin Zhang et al. · arXiv · Aug 18, 2026

  Memory-based self-improving agents--those that learn from an online stream of tasks and improve over time by maintaining a textual memory bank--have shown great promise in recent literature. However, the reliability aspects of these methods…

• Loss-Based Active Learning for Neural Abstractive Summarization
  Michail Ioannou, Tatiana Passali, Grigorios Tsoumakas · Greeks in AI 2026 Poster · Jun 2, 2026

  Fine-tuning abstractive summarization models requires high-quality annotated data. However, obtaining such corpora is expensive and time-consuming, as it requires human annotators to read and comprehend long documents to create accurate sum…

• Active learning framework leveraging transcriptomics identifies modulators of disease phenotypes.
  Benjamin DeMeo, Charlotte Nesbitt, S. A. Miller, Daniel B. Burkhardt et al. · Science · Oct 23, 2025

  Phenotypic drug screening remains constrained by the vastness of chemical space and technical challenges scaling experimental workflows. To overcome these barriers, computational methods have been developed to prioritize compounds, but they…

• InvDesFlow-AL: active learning-based workflow for inverse design of functional materials
  Xiao-Qi Han, Peng-Jie Guo, Ze-Feng Gao, Hao Sun et al. · npj Computational Materials · May 14, 2025

  Developing inverse design methods for functional materials with specific properties is critical to advancing fields like renewable energy, catalysis, energy storage, and carbon capture. Generative models based on diffusion principles can di…

• Large-scale simulation study of active learning models for systematic reviews
  J. Teijema, J. D. Bruin, Ayoub Bagheri, R. Schoot · International Journal of Data Science and Analysis · May 2, 2025

  Despite progress in active learning, evaluation remains limited by constraints in simulation size, infrastructure, and dataset availability. This study advocates for large-scale simulations as the gold standard for evaluating active learnin…

• Digital Twin-Based Active Learning for Industrial Process Control and Supervision in Industry 4.0
  Jessica S. Ortiz, Evelin K. Quishpe, Grace X. Sailema, Nathaly S. Guamán · Italian National Conference on Sensors · Mar 26, 2025

  The integration of Digital Twin technology into active learning environments has been established as an innovative strategy to optimize engineering education. This study focuses on the development and evaluation of a learning tool based on …

• A Novel Active Learning Technique for Fetal Health Classification Based on XGBoost Classifier
  Kaushal Bhardwaj, Niyati Goyal, Bhavika Mittal, Vandna Sharma et al. · IEEE Access · Jan 1, 2025

  Ensuring safe pregnancy and reducing maternal and infant mortality rates require early prediction of fetal health. The application of machine learning algorithms in monitoring fetal health helps to improve the chances of timely intervention…

• DIRECT: Deep Active Learning under Imbalance and Label Noise
  Shyam Nuggehalli, Jifan Zhang, Lalit K Jain, Robert D Nowak · ICLR 2025 Conference Withdrawn Submission · Sep 27, 2024

  Class imbalance is a prevalent issue in real world machine learning applications, often leading to poor performance in rare and minority classes. With an abundance of wild unlabeled data, active learning is perhaps the most effective techni…

• A Cross-Domain Benchmark for Active Learning
  Thorben Werner, Johannes Burchert, Maximilian Stubbemann, Lars Schmidt-Thieme · NeurIPS 2024 Track Datasets and Benchmarks Poster · Sep 26, 2024

  Active Learning (AL) deals with identifying the most informative samples for labeling to reduce data annotation costs for supervised learning tasks. AL research suffers from the fact that lifts from literature generalize poorly and that onl…

• Universal Rates for Active Learning
  Steve Hanneke, Amin Karbasi, Shay Moran, Grigoris Velegkas · NeurIPS 2024 poster · Sep 25, 2024

  In this work we study the problem of actively learning binary classifiers from a given concept class, i.e., learning by utilizing unlabeled data and submitting targeted queries about their labels to a domain expert. We evaluate the q…

• Learnability Matters: Active Learning for Video Captioning
  Yiqian Zhang, Buyu Liu, Jun Bao, Qiang Huang et al. · NeurIPS 2024 poster · Sep 25, 2024

  This work focuses on the active learning in video captioning. In particular, we propose to address the learnability problem in active learning, which has been brought up by collective outliers in video captioning and neglected in the litera…

• Fair Active Learning in Low-Data Regimes
  Romain Camilleri, Andrew Wagenmaker, Kevin Jamieson, Lalit K Jain et al. · UAI 2024 poster · Apr 26, 2024

  In critical machine learning applications, ensuring fairness is essential to avoid perpetuating social inequities. In this work, we address the challenges of reducing bias and improving accuracy in data-scarce environments, where the cost o…

• SUPClust: Active Learning at the Boundaries
  Yuta Ono, Till Aczel, Benjamin Estermann, Roger Wattenhofer · PML4LRS Poster · Mar 5, 2024

  Active learning is a machine learning paradigm designed to optimize model performance in a setting where labeled data is expensive to acquire. In this work, we propose a novel active learning method called SUPClust that seeks to identify po…

• Learning to Rank for One-Round Active Learning
  DMLR @ ICLR 2024 · Mar 4, 2024

  Active learning is a promising paradigm to reduce the labeling cost by strategically requesting labels to improve model performance. However, existing active learning methods often rely on expensive acquisition function to compute, extensiv…

• Neural Active Learning Beyond Bandits
  Yikun Ban, Ishika Agarwal, Ziwei Wu, Yada Zhu et al. · ICLR 2024 poster · Jan 16, 2024

  We study both stream-based and pool-based active learning with neural network approximations. A recent line of works proposed bandit-based approaches that transformed active learning into a bandit problem, achieving both theoretical and emp…

• Active learning for data streams: a survey
  Davide Cacciarelli, Murat Kulahci · Machine Learning · Jan 1, 2024

  Online active learning is a paradigm in machine learning that aims to select the most informative data points to label from a data stream. The problem of minimizing the cost associated with collecting labeled observations has gained a lot o…

• Compute-Efficient Active Learning
  Gábor Németh, Tamas Matuszka · RealML-2023 · Oct 27, 2023

  Active learning, a powerful paradigm in machine learning, aims at reducing labeling costs by selecting the most informative samples from an unlabeled dataset. However, traditional active learning process often demands extensive computationa…

• Exploring Active Learning in Meta-Learning: Enhancing Context Set Labeling
  Wonho Bae, Jing Wang, Danica J. Sutherland · Submitted to ICLR 2024 · Sep 24, 2023

  Most meta-learning methods assume that the (very small) context set used to establish a new task at test time is passively provided. In some settings, however, it is feasible to actively select which points to label; the potential gain from…

• Algorithm Selection for Deep Active Learning with Imbalanced Datasets
  Jifan Zhang, Shuai Shao, saurabh verma, Robert D Nowak · NeurIPS 2023 poster · Sep 21, 2023

  Label efficiency has become an increasingly important objective in deep learning applications. Active learning aims to reduce the number of labeled examples needed to train deep networks, but the empirical performance of active learning alg…

• Active Learning-Based Species Range Estimation
  Christian Lange, Elijah Cole, Grant Van Horn, Oisin Mac Aodha · NeurIPS 2023 poster · Sep 21, 2023

  We propose a new active learning approach for efficiently estimating the geographic range of a species from a limited number of on the ground observations. We model the range of an unmapped species of interest as the weighted combination of…

• Agnostic Multi-Group Active Learning
  Nicholas Rittler, Kamalika Chaudhuri · NeurIPS 2023 poster · Sep 21, 2023

  Inspired by the problem of improving classification accuracy on rare or hard subsets of a population, there has been recent interest in models of learning where the goal is to generalize to a collection of distributions, each representing a…

• Nuclear discrepancy for single-shot batch active learning
  [object Object], [object Object], [object Object] · Machine Learning · Sep 26, 2019

  Active learning algorithms propose what data should be labeled given a pool of unlabeled data. Instead of selecting randomly what data to annotate, active learning strategies aim to select data so as to get a good predictive model with as l…