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 27 篇，第 1 / 1 页

1. ICML 2023A Category-theoretical Meta-analysis of Definitions of Disentanglement
2. ICML 2023A Closer Look at the Intervention Procedure of Concept Bottleneck Models
3. ICML 2023A Kernel-Based View of Language Model Fine-Tuning
4. ICML 2023A Scalable Frank-Wolfe-Based Algorithm for the Max-Cut SDP
5. ICML 2023Adaptively Weighted Data Augmentation Consistency Regularization for Robust Optimization under Concept Shift
6. ICML 2023Causal Proxy Models for Concept-based Model Explanations
7. ICML 2023Cluster Explanation via Polyhedral Descriptions
8. ICML 2023Concept-based Explanations for Out-of-Distribution Detectors
9. ICML 2023Denoising MCMC for Accelerating Diffusion-Based Generative Models
10. ICML 2023Difference-in-Differences Meets Tree-based Methods: Heterogeneous Treatment Effects Estimation with Unmeasured Confounding
11. ICML 2023Discover and Cure: Concept-aware Mitigation of Spurious Correlation
12. ICML 2023Facial Expression Recognition with Adaptive Frame Rate based on Multiple Testing Correction
13. ICML 2023Flash: Concept Drift Adaptation in Federated Learning
14. ICML 2023Geometric Clifford Algebra Networks
15. ICML 2023Interpretable Neural-Symbolic Concept Reasoning
16. ICML 2023Lowering the Pre-training Tax for Gradient-based Subset Training: A Lightweight Distributed Pre-Training Toolkit
17. ICML 2023Neuro-Symbolic Continual Learning: Knowledge, Reasoning Shortcuts and Concept Rehearsal
18. ICML 2023On the Relationship Between Explanation and Prediction: A Causal View
19. ICML 2023Probabilistic Concept Bottleneck Models
20. ICML 2023PWSHAP: A Path-Wise Explanation Model for Targeted Variables
21. ICML 2023Refining Generative Process with Discriminator Guidance in Score-based Diffusion Models
22. ICML 2023Robust Explanation for Free or At the Cost of Faithfulness
23. ICML 2023SlotGAT: Slot-based Message Passing for Heterogeneous Graphs
24. ICML 2023The Implicit Regularization of Dynamical Stability in Stochastic Gradient Descent
25. ICML 2023The Virtues of Laziness in Model-based RL: A Unified Objective and Algorithms
26. ICML 2023Towards Bridging the Gaps between the Right to Explanation and the Right to be Forgotten
27. ICML 2023Towards Trustworthy Explanation: On Causal Rationalization

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。