概念解释论文趋势 2023–2026

主要结论

• 概念解释论文从 2023 年的 91 篇增长到 2026 年的 117 篇，三年间扩大到约 1.3 倍。
• NeurIPS 是发概念解释论文最多的会议，2023–2026 年共 134 篇，占四个会议总量的 39%。
• 交叉方向里涨得最快的是多模态大模型：同时属于两个主题的论文从 2023 年的 4 篇增至 2026 年的 23 篇。
• 在「可解释性」的 5 个主题里，它的 2026 年论文数排第 3；同组增长最快的机制解释是 8.1 倍，概念解释是 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 2026CENDRe: Concept Extraction with Natural Domain Representations
• ICML 2026Evidential Copula Concept Embedding Models
• ICLR 2026Decoupling the Class Label and the Target Concept in Machine Unlearning
• CVPR 2026Agile Deliberation Concept Deliberation for Subjective Visual Classification
• NeurIPS 2025An Analysis of Concept Bottleneck Models: Measuring, Understanding, and Mitigating the Impact of Noisy Annotations
• ICML 2025Concept-Centric Token Interpretation for Vector-Quantized Generative Models
• ICLR 2025Causal Concept Graph Models: Beyond Causal Opacity in Deep Learning
• CVPR 2025Discovering Fine-Grained Visual-Concept Relations by Disentangled Optimal Transport Concept Bottleneck Models
• NeurIPS 2024[Re] On the Reproducibility of Post-Hoc Concept Bottleneck Models
• ICML 2024ContPhy: Continuum Physical Concept Learning and Reasoning from Videos
• ICLR 2024AttEXplore: Attribution for Explanation with model parameters eXploration
• CVPR 2024Fine-Grained Bipartite Concept Factorization for Clustering
• NeurIPS 2023[Re] Hierarchical Shrinkage: Improving the Accuracy and Interpretability of Tree-Based Methods
• ICML 2023A Closer Look at the Intervention Procedure of Concept Bottleneck Models
• ICLR 2023Concept Gradient: Concept-based Interpretation Without Linear Assumption
• CVPR 2023CRAFT: Concept Recursive Activation FacTorization for Explainability
• NeurIPS 2026Concept frustration: Aligning human concepts and machine representations
• ICML 2026On the Variability of Concept Activation Vectors
• ICLR 2026Hierarchical Concept-based Interpretable Models
• CVPR 2026DCoAR Deep Concept Injection into Unified Autoregressive Models for Personalized

全部概念解释论文

共 63 篇，第 1 / 2 页

1. CVPR 2024Adversarially Robust Few-shot Learning via Parameter Co-distillation of Similarity and Class Concept Learners
2. CVPR 2024CLiC: Concept Learning in Context
3. CVPR 2024Comparing the Decision-Making Mechanisms by Transformers and CNNs via Explanation Methods
4. CVPR 2024ConCon-Chi: Concept-Context Chimera Benchmark for Personalized Vision-Language Tasks
5. CVPR 2024CosalPure: Learning Concept from Group Images for Robust Co-Saliency Detection
6. CVPR 2024Discovering and Mitigating Visual Biases through Keyword Explanation
7. CVPR 2024Fine-Grained Bipartite Concept Factorization for Clustering
8. CVPR 2024Incremental Residual Concept Bottleneck Models
9. CVPR 2024Label-Efficient Group Robustness via Out-of-Distribution Concept Curation
10. CVPR 2024MACE: Mass Concept Erasure in Diffusion Models
11. CVPR 2024MCPNet: An Interpretable Classifier via Multi-Level Concept Prototypes
12. CVPR 2024Naturally Supervised 3D Visual Grounding with Language-Regularized Concept Learners
13. CVPR 2024Neural Redshift: Random Networks are not Random Functions
14. ICLR 2024AttEXplore: Attribution for Explanation with model parameters eXploration
15. ICLR 2024Classification with Conceptual Safeguards
16. ICLR 2024Concept Bottleneck Generative Models
17. ICLR 2024Effective pruning of web-scale datasets based on complexity of concept clusters
18. ICLR 2024Energy-Based Concept Bottleneck Models: Unifying Prediction, Concept Intervention, and Probabilistic Interpretations
19. ICLR 2024Faithful Explanations of Black-box NLP Models Using LLM-generated Counterfactuals
20. ICLR 2024On Error Propagation of Diffusion Models
21. ICLR 2024RAPPER: Reinforced Rationale-Prompted Paradigm for Natural Language Explanation in Visual Question Answering
22. ICLR 2024Respect the model: Fine-grained and Robust Explanation with Sharing Ratio Decomposition
23. ICML 2024A Geometric Explanation of the Likelihood OOD Detection Paradox
24. ICML 2024Active Statistical Inference
25. ICML 2024An Image is Worth Multiple Words: Discovering Object Level Concepts using Multi-Concept Prompt Learning
26. ICML 2024Balanced Data, Imbalanced Spectra: Unveiling Class Disparities with Spectral Imbalance
27. ICML 2024ContPhy: Continuum Physical Concept Learning and Reasoning from Videos
28. ICML 2024Easing Concept Bleeding in Diffusion via Entity Localization and Anchoring
29. ICML 2024EiG-Search: Generating Edge-Induced Subgraphs for GNN Explanation in Linear Time
30. ICML 2024Feature Attribution with Necessity and Sufficiency via Dual-stage Perturbation Test for Causal Explanation
31. ICML 2024Finding NEM-U: Explaining unsupervised representation learning through neural network generated explanation masks
32. ICML 2024Gradient-based Visual Explanation for Transformer-based CLIP
33. ICML 2024Learning to Intervene on Concept Bottlenecks
34. ICML 2024Local vs. Global Interpretability: A Computational Complexity Perspective
35. ICML 2024On a Combinatorial Problem Arising in Machine Teaching
36. ICML 2024On Gradient-like Explanation under a Black-box Setting: When Black-box Explanations Become as Good as White-box
37. ICML 2024One for All: A Universal Generator for Concept Unlearnability via Multi-Modal Alignment
38. ICML 2024RICE: Breaking Through the Training Bottlenecks of Reinforcement Learning with Explanation
39. ICML 2024Spider: A Unified Framework for Context-dependent Concept Segmentation
40. ICML 2024Towards Compositionality in Concept Learning
41. ICML 2024Understanding Inter-Concept Relationships in Concept-Based Models
42. ICML 2024Why Do You Grok? A Theoretical Analysis on Grokking Modular Addition
43. NeurIPS 2024[Re] On the Reproducibility of Post-Hoc Concept Bottleneck Models
44. NeurIPS 2024A Concept-Based Explainability Framework for Large Multimodal Models
45. NeurIPS 2024A Neural Network Approach for Efficiently Answering Most Probable Explanation Queries in Probabilistic Models
46. NeurIPS 2024A theoretical design of concept sets: improving the predictability of concept bottleneck models
47. NeurIPS 2024Auditing Local Explanations is Hard
48. NeurIPS 2024Beyond Concept Bottleneck Models: How to Make Black Boxes Intervenable?
49. NeurIPS 2024Coarse-to-Fine Concept Bottleneck Models
50. NeurIPS 2024Defensive Unlearning with Adversarial Training for Robust Concept Erasure in Diffusion Models

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。