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 2 / 4 页

51. ICLR 2025Efficient Active Imitation Learning with Random Network Distillation
52. ICLR 2025Near-optimal Active Regression of Single-Index Models
53. ICLR 2025Provably Accurate Shapley Value Estimation via Leverage Score Sampling
54. ICLR 2025SAVA: Scalable Learning-Agnostic Data Valuation
55. ICLR 2025Uncertainty Herding: One Active Learning Method for All Label Budgets
56. ICML 2025Active Learning of Deep Neural Networks via Gradient-Free Cutting Planes
57. ICML 2025Active Treatment Effect Estimation via Limited Samples
58. ICML 2025AutoAL: Automated Active Learning with Differentiable Query Strategy Search
59. ICML 2025Efficient Heterogeneity-Aware Federated Active Data Selection
60. ICML 2025Importance Sampling for Nonlinear Models
61. ICML 2025Improved Algorithm for Deep Active Learning under Imbalance via Optimal Separation
62. ICML 2025On the Benefits of Active Data Collection in Operator Learning
63. NeurIPS 2025Active Measurement: Efficient Estimation at Scale
64. NeurIPS 2025Active Seriation: Efficient Ordering Recovery with Statistical Guarantees
65. NeurIPS 2025Agnostic Active Learning Is Always Better Than Passive Learning
66. NeurIPS 2025Balanced Active Inference
67. NeurIPS 2025Formal Models of Active Learning from Contrastive Examples
68. NeurIPS 2025Near-Exponential Savings for Population Mean Estimation with Active Learning
69. NeurIPS 2025Robust Sampling for Active Statistical Inference
70. NeurIPS 2025Scaling Up Active Testing to Large Language Models
71. NeurIPS 2025TADA: Improved Diffusion Sampling with Training-free Augmented DynAmics
72. CVPR 2024Active Generalized Category Discovery
73. CVPR 2024Active Prompt Learning in Vision Language Models
74. CVPR 2024ActiveDC: Distribution Calibration for Active Finetuning
75. CVPR 2024NARUTO: Neural Active Reconstruction from Uncertain Target Observations
76. CVPR 2024Neural Visibility Field for Uncertainty-Driven Active Mapping
77. ICLR 2024Embodied Active Defense: Leveraging Recurrent Feedback to Counter Adversarial Patches
78. ICLR 2024IDEAL: Influence-Driven Selective Annotations Empower In-Context Learners in Large Language Models
79. ICLR 2024Improved Active Learning via Dependent Leverage Score Sampling
80. ICLR 2024Neural Active Learning Beyond Bandits
81. ICLR 2024One-shot Active Learning Based on Lewis Weight Sampling for Multiple Deep Models
82. ICLR 2024Querying Easily Flip-flopped Samples for Deep Active Learning
83. ICML 2024Acquisition Conditioned Oracle for Nongreedy Active Feature Acquisition
84. ICML 2024Active Statistical Inference
85. ICML 2024Conditional Normalizing Flows for Active Learning of Coarse-Grained Molecular Representations
86. ICML 2024Defense against Model Extraction Attack by Bayesian Active Watermarking
87. ICML 2024Diffusion Posterior Sampling is Computationally Intractable
88. ICML 2024Fast Co-Training under Weak Dependence via Stream-Based Active Learning
89. ICML 2024Faster Sampling via Stochastic Gradient Proximal Sampler
90. ICML 2024Path-Guided Particle-based Sampling
91. ICML 2024Performance Bounds for Active Binary Testing with Information Maximization
92. ICML 2024Provably Neural Active Learning Succeeds via Prioritizing Perplexing Samples
93. ICML 2024Uncertainty for Active Learning on Graphs
94. NeurIPS 2024Active Classification with Few Queries under Misspecification
95. NeurIPS 2024Active learning of neural population dynamics using two-photon holographic optogenetics
96. NeurIPS 2024Active Set Ordering
97. NeurIPS 2024Active, anytime-valid risk controlling prediction sets
98. NeurIPS 2024Boundary Matters: A Bi-Level Active Finetuning Method
99. NeurIPS 2024Contextual Active Model Selection
100. NeurIPS 2024Fairness without Harm: An Influence-Guided Active Sampling Approach

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。