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 91 篇，第 2 / 2 页

51. NeurIPS 2023Concept Algebra for (Score-Based) Text-Controlled Generative Models
52. NeurIPS 2023Concept Distillation: Leveraging Human-Centered Explanations for Model Improvement
53. NeurIPS 2023Content-based Unrestricted Adversarial Attack
54. NeurIPS 2023D-Separation for Causal Self-Explanation
55. NeurIPS 2023Decompose Novel into Known: Part Concept Learning For 3D Novel Class Discovery
56. NeurIPS 2023Discriminative Calibration: Check Bayesian Computation from Simulations and Flexible Classifier
57. NeurIPS 2023EMBERSim: A Large-Scale Databank for Boosting Similarity Search in Malware Analysis
58. NeurIPS 2023Estimating Propensity for Causality-based Recommendation without Exposure Data
59. NeurIPS 2023Explain Any Concept: Segment Anything Meets Concept-Based Explanation
60. NeurIPS 2023Frequency Domain-Based Dataset Distillation
61. NeurIPS 2023GAIA: Delving into Gradient-based Attribution Abnormality for Out-of-distribution Detection
62. NeurIPS 2023GLIME: General, Stable and Local LIME Explanation
63. NeurIPS 2023Inner Product-based Neural Network Similarity
64. NeurIPS 2023Interpretable Graph Networks Formulate Universal Algebra Conjectures
65. NeurIPS 2023Interpretable Prototype-based Graph Information Bottleneck
66. NeurIPS 2023Kernel Quadrature with Randomly Pivoted Cholesky
67. NeurIPS 2023LEACE: Perfect linear concept erasure in closed form
68. NeurIPS 2023Learning with Explanation Constraints
69. NeurIPS 2023Many-body Approximation for Non-negative Tensors
70. NeurIPS 2023Minimax Forward and Backward Learning of Evolving Tasks with Performance Guarantees
71. NeurIPS 2023Monarch Mixer: A Simple Sub-Quadratic GEMM-Based Architecture
72. NeurIPS 2023NeRF-IBVS: Visual Servo Based on NeRF for Visual Localization and Navigation
73. NeurIPS 2023Non-Asymptotic Analysis of a UCB-based Top Two Algorithm
74. NeurIPS 2023Optimal Extragradient-Based Algorithms for Stochastic Variational Inequalities with Separable Structure
75. NeurIPS 2023Orthogonal Non-negative Tensor Factorization based Multi-view Clustering
76. NeurIPS 2023Reference-Based POMDPs
77. NeurIPS 2023Restless Bandits with Average Reward: Breaking the Uniform Global Attractor Assumption
78. NeurIPS 2023ReSync: Riemannian Subgradient-based Robust Rotation Synchronization
79. NeurIPS 2023Robust Concept Erasure via Kernelized Rate-Distortion Maximization
80. NeurIPS 2023SAME: Uncovering GNN Black Box with Structure-aware Shapley-based Multipiece Explanations
81. NeurIPS 2023Sample based Explanations via Generalized Representers
82. NeurIPS 2023Score-based Data Assimilation
83. NeurIPS 2023SOL: Sampling-based Optimal Linear bounding of arbitrary scalar functions
84. NeurIPS 2023Stable Vectorization of Multiparameter Persistent Homology using Signed Barcodes as Measures
85. NeurIPS 2023Test-time Training for Matching-based Video Object Segmentation
86. NeurIPS 2023The Utility of “Even if” Semifactual Explanation to Optimise Positive Outcomes
87. NeurIPS 2023Time Series Kernels based on Nonlinear Vector AutoRegressive Delay Embeddings
88. NeurIPS 2023Towards Evaluating Transfer-based Attacks Systematically, Practically, and Fairly
89. NeurIPS 2023Training Energy-Based Normalizing Flow with Score-Matching Objectives
90. NeurIPS 2023When Do Transformers Shine in RL? Decoupling Memory from Credit Assignment
91. NeurIPS 2023When Does Confidence-Based Cascade Deferral Suffice?

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。