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

9 papers, page 1 of 1

1. NeurIPS 2025Active Measurement: Efficient Estimation at Scale
2. NeurIPS 2025Active Seriation: Efficient Ordering Recovery with Statistical Guarantees
3. NeurIPS 2025Agnostic Active Learning Is Always Better Than Passive Learning
4. NeurIPS 2025Balanced Active Inference
5. NeurIPS 2025Formal Models of Active Learning from Contrastive Examples
6. NeurIPS 2025Near-Exponential Savings for Population Mean Estimation with Active Learning
7. NeurIPS 2025Robust Sampling for Active Statistical Inference
8. NeurIPS 2025Scaling Up Active Testing to Large Language Models
9. NeurIPS 2025TADA: Improved Diffusion Sampling with Training-free Augmented DynAmics

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.