主动学习论文趋势 2023–2026

主要结论

• 主动学习论文从 2023 年的 58 篇降到 2026 年的 41 篇，热度在回落。
• NeurIPS 是发主动学习论文最多的会议，2023–2026 年共 67 篇，占四个会议总量的 41%。
• 交叉方向里涨得最快的是三维视觉：同时属于两个主题的论文从 2023 年的 0 篇增至 2026 年的 6 篇。
• 在「以数据为中心 AI」的 5 个主题里，它的 2026 年论文数排第 3；同组增长最快的合成数据生成是 1.3 倍，主动学习是 0.7 倍。

代表论文

按年份和会议均匀挑选，方便快速看到每一届的样貌

• 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

全部主动学习论文

共 164 篇，第 1 / 4 页

1. CVPR 2026Active Inference for Micro-Gesture Recognition EFE-Guided Temporal Sampling and Adaptive
2. CVPR 2026Active Perceptual Inference A Corticothalamic-Inspired Dynamic Nested Recurrent Network for
3. CVPR 2026ActiveGrasp Information-Guided Active Grasping with Calibrated Energy-based Model
4. CVPR 2026EventHub Data Factory for Generalizable Event-Based Stereo Networks without Active
5. CVPR 2026FailureAtlas Mapping the Failure Landscape of T2I Models via Active
6. CVPR 2026Federated Active Learning Under Extreme Non-IID and Global Class Imbalance
7. CVPR 2026Paparazzo Active Mapping of Moving 3D Objects
8. CVPR 2026Portable Active Learning for Object Detection
9. CVPR 2026SparseOIT Improving Order-Independent Transparency 3DGS via Active Set Method
10. CVPR 2026Uncertainty-driven 3D Gaussian Splatting Active Mapping via Anisotropic Visibility Field
11. ICLR 2026Active Learning for Decision Trees with Provable Guarantees
12. ICLR 2026ActiveCQ: Active Estimation of Causal Quantities
13. ICLR 2026Dynamics-Predictive Sampling for Active RL Finetuning of Large Reasoning Models
14. ICLR 2026PEERING INTO THE UNKNOWN: ACTIVE VIEW SELECTION WITH NEURAL UNCERTAINTY MAPS FOR 3D RECONSTRUCTION
15. ICLR 2026PSP: Prompt-Guided Self-Training Sampling Policy for Active Prompt Learning
16. ICLR 2026TESSAR: Geometry-Aware Active Regression via Dynamic Voronoi Tessellation
17. ICML 2026Active Curriculum Refinement for Reinforcement Learning
18. ICML 2026Active Learning with Low-Rank Structure for Data Selection
19. ICML 2026Active Regression for Single-Index Models with Unknown Link Functions
20. ICML 2026Active Timepoint Selection for Learning Measure-Valued Trajectories
21. ICML 2026BALLAST: Bayesian Active Learning with Look-ahead Amendment for Sea-drifter Trajectories under Spatio-Temporal Vector Fields
22. ICML 2026Distributional Active Inference
23. ICML 2026Learning $U$-Statistics with Active Inference
24. ICML 2026MA$^3$S: Model-Agnostic Active Annotation Strategy for Crowdsourcing
25. NeurIPS 2026Active Corpus Selection for Training Subgraph Retrievers Using OOD Queries
26. NeurIPS 2026Active Learning as Nullspace Regulation: A Spectral Representation Perspective
27. NeurIPS 2026Active Learning for Conditional Generative Compressed Sensing
28. NeurIPS 2026Beyond Langevin: Sampling Multimodal Densities using the Witten Laplacian on 1-forms
29. NeurIPS 2026Do Glimpse Policies See Like Humans? A Behavioral Audit Reveals Dissociated Viewing Priors in Classification-Trained Active Vision
30. NeurIPS 2026Fixed-Size Active Statistical Inference
31. NeurIPS 2026Forgetting to Improve: Principled Data Removal in Active Learning
32. NeurIPS 2026Gumbo: Gumbel Optimized High-Temperature Speculative Sampling
33. NeurIPS 2026How New Strategies Emerge in RL Post-Training: A Controlled Study
34. NeurIPS 2026LLM Active Alignment: A Nash Equilibrium Perspective
35. NeurIPS 2026Online Active Testing: Adaptive Importance Sampling for Unbiased Risk Estimation in Data Streams
36. NeurIPS 2026Post-ADC Inference: Valid Inference After Active Data Collection
37. NeurIPS 2026Prediction-Powered Active Testing
38. NeurIPS 2026Safe Active Learning with Future Viability Guarantees in Time-Series Models
39. NeurIPS 2026Tactile MNIST: Benchmarking Active Tactile Perception
40. NeurIPS 2026Towards instance-dependent regret optimality in Episodic MDPs with Posterior Sampling
41. CVPR 2025Active Data Curation Effectively Distills Large-Scale Multimodal Models
42. CVPR 2025Active Hyperspectral Imaging Using an Event Camera
43. CVPR 2025EnliveningGS: Active Locomotion of 3DGS
44. CVPR 2025Learning Extremely High Density Crowds as Active Matters
45. CVPR 2025RaSS: Improving Denoising Diffusion Samplers with Reinforced Active Sampling Scheduler
46. CVPR 2025Rethinking Epistemic and Aleatoric Uncertainty for Active Open-Set Annotation: An Energy-Based Approach
47. CVPR 2025Towards Cost-Effective Learning: A Synergy of Semi-Supervised and Active Learning
48. CVPR 2025Uncertainty Meets Diversity: A Comprehensive Active Learning Framework for Indoor 3D Object Detection
49. ICLR 2025Active Learning for Continual Learning: Keeping the Past Alive in the Present
50. ICLR 2025Dual Process Learning: Controlling Use of In-Context vs. In-Weights Strategies with Weight Forgetting

常见问题

2023–2026 年四大会议一共有多少篇主动学习论文？

共 165 篇，按年份分别是 2023 年 58 篇、2024 年 35 篇、2025 年 31 篇、2026 年 41 篇。

NeurIPS 2026 有多少篇主动学习论文？

NeurIPS 2026 有 16 篇主动学习论文，上一届是 9 篇。

ICLR 2026 有多少篇主动学习论文？

ICLR 2026 有 6 篇主动学习论文，上一届是 7 篇。

ICML 2026 有多少篇主动学习论文？

ICML 2026 有 8 篇主动学习论文，上一届是 7 篇。

CVPR 2026 有多少篇主动学习论文？

CVPR 2026 有 11 篇主动学习论文，上一届是 8 篇。

哪个会议的主动学习论文最多？

NeurIPS，2023–2026 年共 67 篇。