Active Learning papers, 2023–2026

Key findings

• Active Learning fell from 58 papers in 2023 to 41 in 2026, so interest is cooling.
• NeurIPS publishes the most Active Learning work: 67 papers from 2023 to 2026, 41% of the four-venue total.
• The fastest-growing overlap is with 3D Vision: papers tagged with both rose from 0 in 2023 to 6 in 2026.
• Among the 5 topics under Data-Centric AI, it ranks #3 by 2026 paper count; the fastest grower in the group, Synthetic Data Generation, is up 1.3x versus 0.7x here.

Representative papers

Spread across years and venues so every edition shows up

• NeurIPS 2026Active Corpus Selection for Training Subgraph Retrievers Using OOD Queries
• ICML 2026Active Regression for Single-Index Models with Unknown Link Functions
• ICLR 2026ActiveCQ: Active Estimation of Causal Quantities
• CVPR 2026Active Inference for Micro-Gesture Recognition EFE-Guided Temporal Sampling and Adaptive
• NeurIPS 2025Active Measurement: Efficient Estimation at Scale
• ICML 2025Active Learning of Deep Neural Networks via Gradient-Free Cutting Planes
• ICLR 2025Dual Process Learning: Controlling Use of In-Context vs. In-Weights Strategies with Weight Forgetting
• CVPR 2025Active Hyperspectral Imaging Using an Event Camera
• NeurIPS 2024On the Convergence of Loss and Uncertainty-based Active Learning Algorithms
• ICML 2024Active Statistical Inference
• ICLR 2024Improved Active Learning via Dependent Leverage Score Sampling
• CVPR 2024NARUTO: Neural Active Reconstruction from Uncertain Target Observations
• NeurIPS 2023A Competitive Algorithm for Agnostic Active Learning
• ICML 2023A Two-Stage Active Learning Algorithm for k-Nearest Neighbors
• ICLR 2023A Simple Yet Powerful Deep Active Learning With Snapshots Ensembles
• CVPR 2023Re-Thinking Federated Active Learning Based on Inter-Class Diversity
• NeurIPS 2026Active Learning as Nullspace Regulation: A Spectral Representation Perspective
• ICML 2026Active Timepoint Selection for Learning Measure-Valued Trajectories
• ICLR 2026TESSAR: Geometry-Aware Active Regression via Dynamic Voronoi Tessellation
• CVPR 2026EventHub Data Factory for Generalizable Event-Based Stereo Networks without Active

All Active Learning papers

35 papers, page 1 of 1

1. CVPR 2024Active Generalized Category Discovery
2. CVPR 2024Active Prompt Learning in Vision Language Models
3. CVPR 2024ActiveDC: Distribution Calibration for Active Finetuning
4. CVPR 2024NARUTO: Neural Active Reconstruction from Uncertain Target Observations
5. CVPR 2024Neural Visibility Field for Uncertainty-Driven Active Mapping
6. ICLR 2024Embodied Active Defense: Leveraging Recurrent Feedback to Counter Adversarial Patches
7. ICLR 2024IDEAL: Influence-Driven Selective Annotations Empower In-Context Learners in Large Language Models
8. ICLR 2024Improved Active Learning via Dependent Leverage Score Sampling
9. ICLR 2024Neural Active Learning Beyond Bandits
10. ICLR 2024One-shot Active Learning Based on Lewis Weight Sampling for Multiple Deep Models
11. ICLR 2024Querying Easily Flip-flopped Samples for Deep Active Learning
12. ICML 2024Acquisition Conditioned Oracle for Nongreedy Active Feature Acquisition
13. ICML 2024Active Statistical Inference
14. ICML 2024Conditional Normalizing Flows for Active Learning of Coarse-Grained Molecular Representations
15. ICML 2024Defense against Model Extraction Attack by Bayesian Active Watermarking
16. ICML 2024Diffusion Posterior Sampling is Computationally Intractable
17. ICML 2024Fast Co-Training under Weak Dependence via Stream-Based Active Learning
18. ICML 2024Faster Sampling via Stochastic Gradient Proximal Sampler
19. ICML 2024Path-Guided Particle-based Sampling
20. ICML 2024Performance Bounds for Active Binary Testing with Information Maximization
21. ICML 2024Provably Neural Active Learning Succeeds via Prioritizing Perplexing Samples
22. ICML 2024Uncertainty for Active Learning on Graphs
23. NeurIPS 2024Active Classification with Few Queries under Misspecification
24. NeurIPS 2024Active learning of neural population dynamics using two-photon holographic optogenetics
25. NeurIPS 2024Active Set Ordering
26. NeurIPS 2024Active, anytime-valid risk controlling prediction sets
27. NeurIPS 2024Boundary Matters: A Bi-Level Active Finetuning Method
28. NeurIPS 2024Contextual Active Model Selection
29. NeurIPS 2024Fairness without Harm: An Influence-Guided Active Sampling Approach
30. NeurIPS 2024GOMAA-Geo: GOal Modality Agnostic Active Geo-localization
31. NeurIPS 2024HOPE: Shape Matching Via Aligning Different K-hop Neighbourhoods
32. NeurIPS 2024On the Convergence of Loss and Uncertainty-based Active Learning Algorithms
33. NeurIPS 2024Robust Offline Active Learning on Graphs
34. NeurIPS 2024SEL-BALD: Deep Bayesian Active Learning with Selective Labels
35. NeurIPS 2024Universal Rates for Active Learning

FAQ

How many Active Learning papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

165 in total: 58 in 2023, 35 in 2024, 31 in 2025, 41 in 2026.

How many Active Learning papers are at NeurIPS 2026?

NeurIPS 2026 has 16 Active Learning papers, versus 9 the year before.

How many Active Learning papers are at ICLR 2026?

ICLR 2026 has 6 Active Learning papers, versus 7 the year before.

How many Active Learning papers are at ICML 2026?

ICML 2026 has 8 Active Learning papers, versus 7 the year before.

How many Active Learning papers are at CVPR 2026?

CVPR 2026 has 11 Active Learning papers, versus 8 the year before.

Which conference publishes the most Active Learning papers?

NeurIPS, with 67 papers from 2023 to 2026.