弱监督论文趋势 2023–2026

启发式标注

统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 136 篇被归入该主题的论文。

主要结论

每年论文数

各会议论文数

按年份和会议统计

弱监督论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
202341051534
20241136727
20251592430
2026128151045

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

全部弱监督论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 136 篇，第 2 / 3 页

  1. ICLR 2025Iterative Label Refinement Matters More than Preference Optimization under Weak Supervision
  2. ICLR 2025LASER: A Neuro-Symbolic Framework for Learning Spatio-Temporal Scene Graphs with Weak Supervision
  3. ICLR 2025Learning from weak labelers as constraints
  4. ICLR 2025Provable weak-to-strong generalization via benign overfitting
  5. ICLR 2025SMI-Editor: Edit-based SMILES Language Model with Fragment-level Supervision
  6. ICLR 2025Super(ficial)-alignment: Strong Models May Deceive Weak Models in Weak-to-Strong Generalization
  7. ICLR 2025Weak to Strong Generalization for Large Language Models with Multi-capabilities
  8. ICLR 2025Your Weak LLM is Secretly a Strong Teacher for Alignment
  9. ICML 2025How does Labeling Error Impact Contrastive Learning? A Perspective from Data Dimensionality Reduction
  10. ICML 2025Representations Shape Weak-to-Strong Generalization: Theoretical Insights and Empirical Predictions
  11. NeurIPS 2025Advancing Machine-Generated Text Detection from an Easy to Hard Supervision Perspective
  12. NeurIPS 2025Disentangled Cross-Modal Representation Learning with Enhanced Mutual Supervision
  13. NeurIPS 2025Disentangling Latent Shifts of In-Context Learning with Weak Supervision
  14. NeurIPS 2025Escaping Collapse: The Strength of Weak Data for Large Language Model Training
  15. NeurIPS 2025From Linear to Nonlinear: Provable Weak-to-Strong Generalization through Feature Learning
  16. NeurIPS 2025Learning from Interval Targets
  17. NeurIPS 2025MutualVPR: A Mutual Learning Framework for Resolving Supervision Inconsistencies via Adaptive Clustering
  18. NeurIPS 2025On the Mechanisms of Weak-to-Strong Generalization: A Theoretical Perspective
  19. NeurIPS 2025Revisiting Agnostic Boosting
  20. NeurIPS 2025Revisiting End-to-End Learning with Slide-level Supervision in Computational Pathology
  21. NeurIPS 2025Robust Label Proportions Learning
  22. NeurIPS 2025SEGA: Shaping Semantic Geometry for Robust Hashing under Noisy Supervision
  23. NeurIPS 2025Statistical Analysis of an Adversarial Bayesian Weak Supervision Method
  24. NeurIPS 2025Weak-to-Strong Generalization under Distribution Shifts
  25. NeurIPS 2025Weaver: Shrinking the Generation-Verification Gap by Scaling Compute for Verification
  26. CVPR 2024Atom-Level Optical Chemical Structure Recognition with Limited Supervision
  27. CVPR 2024Enhancing Visual Continual Learning with Language-Guided Supervision
  28. CVPR 2024Improving Distant 3D Object Detection Using 2D Box Supervision
  29. CVPR 2024Molecular Data Programming: Towards Molecule Pseudo-labeling with Systematic Weak Supervision
  30. CVPR 2024MS-DETR: Efficient DETR Training with Mixed Supervision
  31. CVPR 2024PointOBB: Learning Oriented Object Detection via Single Point Supervision
  32. CVPR 2024SEAS: ShapE-Aligned Supervision for Person Re-Identification
  33. ICLR 2024Adversarial Supervision Makes Layout-to-Image Diffusion Models Thrive
  34. ICLR 2024Towards a statistical theory of data selection under weak supervision
  35. ICLR 2024Tractable Probabilistic Graph Representation Learning with Graph-Induced Sum-Product Networks
  36. ICML 2024A General Framework for Learning from Weak Supervision
  37. ICML 2024Fast Co-Training under Weak Dependence via Stream-Based Active Learning
  38. ICML 2024On the Effectiveness of Supervision in Asymmetric Non-Contrastive Learning
  39. ICML 2024ULAREF: A Unified Label Refinement Framework for Learning with Inaccurate Supervision
  40. ICML 2024Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision
  41. ICML 2024WISER: Weak Supervision and Supervised Representation Learning to Improve Drug Response Prediction in Cancer
  42. NeurIPS 2024Intrinsic Self-Supervision for Data Quality Audits
  43. NeurIPS 2024Metrizing Weak Convergence with Maximum Mean Discrepancies
  44. NeurIPS 2024On scalable oversight with weak LLMs judging strong LLMs
  45. NeurIPS 2024Quantifying the Gain in Weak-to-Strong Generalization
  46. NeurIPS 2024Segment Anything without Supervision
  47. NeurIPS 2024Smoothie: Label Free Language Model Routing
  48. NeurIPS 2024Stronger Than You Think: Benchmarking Weak Supervision on Realistic Tasks
  49. NeurIPS 2024The ALCHEmist: Automated Labeling 500x CHEaper than LLM Data Annotators
  50. NeurIPS 2024The Many Faces of Optimal Weak-to-Strong Learning

在 Claude、Cursor 里直接问这个趋势

接上 Paperlist MCP 后，写综述、挑方向或准备投稿时，不用离开对话框就能拿到这页的数字：每年各会议的论文数、增长倍数、涨得最快的子方向和代表论文，AI 会按你的问题整理。

可以直接复制这句话问 AI

用 paperlist 查弱监督在 NeurIPS 2023–2026 的论文趋势，哪一年涨得最快？

AI 会调用的工具：get_topic_stats {"topic": "weak-supervision"}

两分钟接入 Paperlist MCP（Claude Code、Cursor、Codex、ChatGPT）

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。

「以数据为中心 AI」下的其他主题