弱监督论文趋势 2023–2026

主要结论

• 弱监督论文从 2023 年的 34 篇增长到 2026 年的 45 篇，三年间扩大到约 1.3 倍。
• NeurIPS 是发弱监督论文最多的会议，2023–2026 年共 42 篇，占四个会议总量的 31%。
• 交叉方向里涨得最快的是对齐与安全：同时属于两个主题的论文从 2023 年的 0 篇增至 2026 年的 7 篇。
• 在「以数据为中心 AI」的 5 个主题里，它的 2026 年论文数排第 2；同组增长最快的合成数据生成是 1.3 倍，弱监督是 1.3 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 2026Affine-invariant Cubic Newton with Weak Learners
• ICML 2026Weak-to-Strong Generalization via Bregman Bias–Variance Decomposition
• ICLR 2026Weak-to-Strong Generalization with Failure Trajectories
• CVPR 2026GEM-TFL Bridging Weak and Full Supervision for Forgery Localization through
• NeurIPS 2025Disentangled Cross-Modal Representation Learning with Enhanced Mutual Supervision
• ICML 2025How does Labeling Error Impact Contrastive Learning? A Perspective from Data Dimensionality Reduction
• ICLR 2025LASER: A Neuro-Symbolic Framework for Learning Spatio-Temporal Scene Graphs with Weak Supervision
• CVPR 2025Bridge the Gap: From Weak to Full Supervision for Temporal Action Localization with PseudoFormer
• NeurIPS 2024Metrizing Weak Convergence with Maximum Mean Discrepancies
• ICML 2024A General Framework for Learning from Weak Supervision
• ICLR 2024Tractable Probabilistic Graph Representation Learning with Graph-Induced Sum-Product Networks
• CVPR 2024Molecular Data Programming: Towards Molecule Pseudo-labeling with Systematic Weak Supervision
• NeurIPS 2023Latent Graph Inference with Limited Supervision
• ICML 2023AdaBoost is not an Optimal Weak to Strong Learner
• ICLR 2023Generative Modeling Helps Weak Supervision (and Vice Versa)
• CVPR 2023DPF: Learning Dense Prediction Fields With Weak Supervision
• NeurIPS 2026Clustering with Weak Distance Oracles
• ICML 2026Learning Permutation from Structure Without Supervision
• ICLR 2026Language-guided Open-world Video Anomaly Detection under Weak Supervision
• CVPR 2026Generalizable Video Quality Assessment via Weak-to-Strong Learning

全部弱监督论文

共 42 篇，第 1 / 1 页

1. NeurIPS 2026Affine-invariant Cubic Newton with Weak Learners
2. NeurIPS 2026CAPER: Clause-Aligned Process Supervision for Text-to-SQL
3. NeurIPS 2026Clustering with Weak Distance Oracles
4. NeurIPS 2026From Patches to Trajectories: Privileged Process Supervision for Software-Engineering Agents
5. NeurIPS 2026Irreducible Supervision Enables Compositional Generalization in Post-Training
6. NeurIPS 2026Label-Free Consistency Correction for Weak-to-Strong Generalization
7. NeurIPS 2026Measuring Weak-to-Strong Legibility of Reasoning Models
8. NeurIPS 2026Neurosymbolic Object-Centric Learning with Distant Supervision
9. NeurIPS 2026Scalable Adaptation of 3D Geometric Foundation Models via Weak Supervision from Internet Video
10. NeurIPS 2026Uncertainty-Aware Probabilistic Constrained Clustering from Entangled Pairwise Supervision
11. NeurIPS 2026Uniform-in-Time Weak Propagation of Chaos in Shallow Neural Networks
12. NeurIPS 2026Your Teacher Can’t Help You Here: Combating Supervision Fidelity Decay in On-Policy Distillation
13. NeurIPS 2025Advancing Machine-Generated Text Detection from an Easy to Hard Supervision Perspective
14. NeurIPS 2025Disentangled Cross-Modal Representation Learning with Enhanced Mutual Supervision
15. NeurIPS 2025Disentangling Latent Shifts of In-Context Learning with Weak Supervision
16. NeurIPS 2025Escaping Collapse: The Strength of Weak Data for Large Language Model Training
17. NeurIPS 2025From Linear to Nonlinear: Provable Weak-to-Strong Generalization through Feature Learning
18. NeurIPS 2025Learning from Interval Targets
19. NeurIPS 2025MutualVPR: A Mutual Learning Framework for Resolving Supervision Inconsistencies via Adaptive Clustering
20. NeurIPS 2025On the Mechanisms of Weak-to-Strong Generalization: A Theoretical Perspective
21. NeurIPS 2025Revisiting Agnostic Boosting
22. NeurIPS 2025Revisiting End-to-End Learning with Slide-level Supervision in Computational Pathology
23. NeurIPS 2025Robust Label Proportions Learning
24. NeurIPS 2025SEGA: Shaping Semantic Geometry for Robust Hashing under Noisy Supervision
25. NeurIPS 2025Statistical Analysis of an Adversarial Bayesian Weak Supervision Method
26. NeurIPS 2025Weak-to-Strong Generalization under Distribution Shifts
27. NeurIPS 2025Weaver: Shrinking the Generation-Verification Gap by Scaling Compute for Verification
28. NeurIPS 2024Intrinsic Self-Supervision for Data Quality Audits
29. NeurIPS 2024Metrizing Weak Convergence with Maximum Mean Discrepancies
30. NeurIPS 2024On scalable oversight with weak LLMs judging strong LLMs
31. NeurIPS 2024Quantifying the Gain in Weak-to-Strong Generalization
32. NeurIPS 2024Segment Anything without Supervision
33. NeurIPS 2024Smoothie: Label Free Language Model Routing
34. NeurIPS 2024Stronger Than You Think: Benchmarking Weak Supervision on Realistic Tasks
35. NeurIPS 2024The ALCHEmist: Automated Labeling 500x CHEaper than LLM Data Annotators
36. NeurIPS 2024The Many Faces of Optimal Weak-to-Strong Learning
37. NeurIPS 2024Theoretical Analysis of Weak-to-Strong Generalization
38. NeurIPS 2024Weak Supervision Performance Evaluation via Partial Identification
39. NeurIPS 2023All Points Matter: Entropy-Regularized Distribution Alignment for Weakly-supervised 3D Segmentation
40. NeurIPS 2023Characterizing the Impacts of Semi-supervised Learning for Weak Supervision
41. NeurIPS 2023Latent Graph Inference with Limited Supervision
42. NeurIPS 2023Mitigating Source Bias for Fairer Weak Supervision

常见问题

2023–2026 年四大会议一共有多少篇弱监督论文？

共 136 篇，按年份分别是 2023 年 34 篇、2024 年 27 篇、2025 年 30 篇、2026 年 45 篇。

NeurIPS 2026 有多少篇弱监督论文？

NeurIPS 2026 有 12 篇弱监督论文，上一届是 15 篇。

ICLR 2026 有多少篇弱监督论文？

ICLR 2026 有 8 篇弱监督论文，上一届是 9 篇。

ICML 2026 有多少篇弱监督论文？

ICML 2026 有 15 篇弱监督论文，上一届是 2 篇。

CVPR 2026 有多少篇弱监督论文？

CVPR 2026 有 10 篇弱监督论文，上一届是 4 篇。

哪个会议的弱监督论文最多？

NeurIPS，2023–2026 年共 42 篇。