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 20 篇，第 1 / 1 页

1. ICML 2026ConEx: Human-Interpretable Saliency Maps via Concept-Aware Attribution
2. ICML 2026Erased but Not Forgotten: How Backdoors Compromise Concept Erasure
3. ICML 2026Evidential Copula Concept Embedding Models
4. ICML 2026Explaining Concept Shift with Interpretable Feature Attribution
5. ICML 2026Explanations are a Means to an End: Decision Theoretic Explanation Evaluation
6. ICML 2026Formal Concept Lattices are Good Semantic Scaffolds for Concept-Based Learning
7. ICML 2026General Quantification of Covariate and Concept Shifts
8. ICML 2026Gradient Testing and Estimation by Comparisons
9. ICML 2026Learning Partial Concept Classes and Universal Rates Under Massart Noise
10. ICML 2026Mixture of Concept Bottleneck Experts
11. ICML 2026MoSSP: A Momentum-Based Single-Loop Stochastic Penalty Method for Nonconvex Constrained DC-regularized Optimization
12. ICML 2026Neural Concept Verifier: Scaling Prover-Verifier Games via Concept Encodings
13. ICML 2026Neuro-Fuzzy Concept Learning for Interpretable Large Multimodal Models
14. ICML 2026On Learnability and Disambiguation of Multiclass Partial Concept Classes
15. ICML 2026On the Variability of Concept Activation Vectors
16. ICML 2026Polaris: Coupled Orbital Polar Embeddings for Hierarchical Concept Learning
17. ICML 2026PPDL: LLM-Based Flows as Probabilistic Programs
18. ICML 2026Prototype-Grounded Concept Models for Verifiable Concept Alignment
19. ICML 2026RC-FCL: Combating Asynchronous Concept Drift in Federated Continual Learning via Retrospective Calibration
20. ICML 2026What LLMs Explain Is Not What They Believe: Evaluating Explanation Sufficiency Under Models' Own Input Beliefs

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。