概念解释论文趋势 2023–2026

TCAV 等

统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 342 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

概念解释论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
202348927791
2024219201363
20252519111671
202640242033117

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

全部概念解释论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 342 篇，第 5 / 7 页

  1. CVPR 2024Neural Redshift: Random Networks are not Random Functions
  2. ICLR 2024AttEXplore: Attribution for Explanation with model parameters eXploration
  3. ICLR 2024Classification with Conceptual Safeguards
  4. ICLR 2024Concept Bottleneck Generative Models
  5. ICLR 2024Effective pruning of web-scale datasets based on complexity of concept clusters
  6. ICLR 2024Energy-Based Concept Bottleneck Models: Unifying Prediction, Concept Intervention, and Probabilistic Interpretations
  7. ICLR 2024Faithful Explanations of Black-box NLP Models Using LLM-generated Counterfactuals
  8. ICLR 2024On Error Propagation of Diffusion Models
  9. ICLR 2024RAPPER: Reinforced Rationale-Prompted Paradigm for Natural Language Explanation in Visual Question Answering
  10. ICLR 2024Respect the model: Fine-grained and Robust Explanation with Sharing Ratio Decomposition
  11. ICML 2024A Geometric Explanation of the Likelihood OOD Detection Paradox
  12. ICML 2024Active Statistical Inference
  13. ICML 2024An Image is Worth Multiple Words: Discovering Object Level Concepts using Multi-Concept Prompt Learning
  14. ICML 2024Balanced Data, Imbalanced Spectra: Unveiling Class Disparities with Spectral Imbalance
  15. ICML 2024ContPhy: Continuum Physical Concept Learning and Reasoning from Videos
  16. ICML 2024Easing Concept Bleeding in Diffusion via Entity Localization and Anchoring
  17. ICML 2024EiG-Search: Generating Edge-Induced Subgraphs for GNN Explanation in Linear Time
  18. ICML 2024Feature Attribution with Necessity and Sufficiency via Dual-stage Perturbation Test for Causal Explanation
  19. ICML 2024Finding NEM-U: Explaining unsupervised representation learning through neural network generated explanation masks
  20. ICML 2024Gradient-based Visual Explanation for Transformer-based CLIP
  21. ICML 2024Learning to Intervene on Concept Bottlenecks
  22. ICML 2024Local vs. Global Interpretability: A Computational Complexity Perspective
  23. ICML 2024On a Combinatorial Problem Arising in Machine Teaching
  24. ICML 2024On Gradient-like Explanation under a Black-box Setting: When Black-box Explanations Become as Good as White-box
  25. ICML 2024One for All: A Universal Generator for Concept Unlearnability via Multi-Modal Alignment
  26. ICML 2024RICE: Breaking Through the Training Bottlenecks of Reinforcement Learning with Explanation
  27. ICML 2024Spider: A Unified Framework for Context-dependent Concept Segmentation
  28. ICML 2024Towards Compositionality in Concept Learning
  29. ICML 2024Understanding Inter-Concept Relationships in Concept-Based Models
  30. ICML 2024Why Do You Grok? A Theoretical Analysis on Grokking Modular Addition
  31. NeurIPS 2024[Re] On the Reproducibility of Post-Hoc Concept Bottleneck Models
  32. NeurIPS 2024A Concept-Based Explainability Framework for Large Multimodal Models
  33. NeurIPS 2024A Neural Network Approach for Efficiently Answering Most Probable Explanation Queries in Probabilistic Models
  34. NeurIPS 2024A theoretical design of concept sets: improving the predictability of concept bottleneck models
  35. NeurIPS 2024Auditing Local Explanations is Hard
  36. NeurIPS 2024Beyond Concept Bottleneck Models: How to Make Black Boxes Intervenable?
  37. NeurIPS 2024Coarse-to-Fine Concept Bottleneck Models
  38. NeurIPS 2024Defensive Unlearning with Adversarial Training for Robust Concept Erasure in Diffusion Models
  39. NeurIPS 2024Do LLMs dream of elephants (when told not to)? Latent concept association and associative memory in transformers
  40. NeurIPS 2024From Causal to Concept-Based Representation Learning
  41. NeurIPS 2024Improving Decision Sparsity
  42. NeurIPS 2024Interpretable Concept Bottlenecks to Align Reinforcement Learning Agents
  43. NeurIPS 2024Interpretable Concept-Based Memory Reasoning
  44. NeurIPS 2024Interpreting CLIP with Sparse Linear Concept Embeddings (SpLiCE)
  45. NeurIPS 2024Neural Concept Binder
  46. NeurIPS 2024PaCE: Parsimonious Concept Engineering for Large Language Models
  47. NeurIPS 2024Relational Concept Bottleneck Models
  48. NeurIPS 2024Stochastic Concept Bottleneck Models
  49. NeurIPS 2024Towards Multi-dimensional Explanation Alignment for Medical Classification
  50. NeurIPS 2024Training for Stable Explanation for Free

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 查概念解释在 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": "concept-based-explanation"}

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概念解释论文？
共 342 篇，按年份分别是 2023 年 91 篇、2024 年 63 篇、2025 年 71 篇、2026 年 117 篇。
NeurIPS 2026 有多少篇概念解释论文？
NeurIPS 2026 有 40 篇概念解释论文，上一届是 25 篇。
ICLR 2026 有多少篇概念解释论文？
ICLR 2026 有 24 篇概念解释论文，上一届是 19 篇。
ICML 2026 有多少篇概念解释论文？
ICML 2026 有 20 篇概念解释论文，上一届是 11 篇。
CVPR 2026 有多少篇概念解释论文？
CVPR 2026 有 33 篇概念解释论文，上一届是 16 篇。
哪个会议的概念解释论文最多？
NeurIPS，2023–2026 年共 134 篇。

「可解释性」下的其他主题