因果发现论文趋势 2023–2026

主要结论

• 因果发现论文从 2023 年的 59 篇增长到 2026 年的 139 篇，三年间扩大到约 2.4 倍。
• NeurIPS 是发因果发现论文最多的会议，2023–2026 年共 150 篇，占四个会议总量的 40%。
• 交叉方向里涨得最快的是通用机器学习 · unsupervised and semisupervised learning：同时属于两个主题的论文从 2023 年的 3 篇增至 2026 年的 10 篇。
• 在「因果与公平」的 5 个主题里，它的 2026 年论文数排第 1；同组增长最快的偏见缓解是 1.5 倍，因果发现是 2.4 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 2026A Characterization of Latent Variable Causal Models Consistent with Observational Data
• ICML 2026A Recursive Decomposition Framework for Causal Structure Learning in the Presence of Latent Variables
• ICLR 2026Bures Generalized Category Discovery
• CVPR 2026Learning by Analogy A Causal Framework for Compositional Generalization
• NeurIPS 2025Causal Differentiating Concepts: Interpreting LM Behavior via Causal Representation Learning
• ICML 2025Bayesian Active Learning for Bivariate Causal Discovery
• ICLR 2025A Conditional Independence Test in the Presence of Discretization
• CVPR 2025Hyperbolic Category Discovery
• NeurIPS 2024Causal Bandits for Linear Structural Equation Models
• ICML 2024Adaptive Online Experimental Design for Causal Discovery
• ICLR 2024A Versatile Causal Discovery Framework to Allow Causally-Related Hidden Variables
• CVPR 2024Contrastive Mean-Shift Learning for Generalized Category Discovery
• NeurIPS 2023A Scale-Invariant Sorting Criterion to Find a Causal Order in Additive Noise Models
• ICML 2023Active causal structure learning with advice
• ICLR 2023Boosting Causal Discovery via Adaptive Sample Reweighting
• CVPR 2023Intrinsic Physical Concepts Discovery With Object-Centric Predictive Models
• NeurIPS 2026Act, Validate, Adapt: Closing the Causal Discovery-Control Loop
• ICML 2026Causal Discovery for Irregularly Time Series with Consistency Guarantees
• ICLR 2026Causal Discovery in the Wild: A Voting-Theoretic Ensemble Approach
• CVPR 2026PlanaReLoc Camera Relocalization in 3D Planar Primitives via Region-Based Structure

全部因果发现论文

共 133 篇，第 2 / 3 页

51. ICML 2026TopoDistill: Distilling Global System Topology for Causal Discovery in Multivariate Time Series
52. ICML 2026Towards Completeness in Causal Discovery from Soft Interventions with Known Targets
53. ICML 2026Unveiling the Structure of Do-Calculus Reasoning via Derivation Graphs
54. ICML 2026Use What You Know: Causal Foundation Models with Partial Graphs
55. ICML 2025A Causal World Model Underlying Next Token Prediction: Exploring GPT in a Controlled Environment
56. ICML 2025An Efficient Search-and-Score Algorithm for Ancestral Graphs using Multivariate Information Scores for Complex Non-linear and Categorical Data
57. ICML 2025Arrow: Accelerator for Time Series Causal Discovery with Time Weaving
58. ICML 2025Bayesian Active Learning for Bivariate Causal Discovery
59. ICML 2025Bivariate Causal Discovery with Proxy Variables: Integral Solving and Beyond
60. ICML 2025Causal Abstraction Inference under Lossy Representations
61. ICML 2025Causal Abstraction Learning based on the Semantic Embedding Principle
62. ICML 2025Causal Discovery from Conditionally Stationary Time Series
63. ICML 2025Continuous Bayesian Model Selection for Multivariate Causal Discovery
64. ICML 2025Differentiable Structure Learning with Ancestral Constraints
65. ICML 2025Discovering Latent Causal Graphs from Spatiotemporal Data
66. ICML 2025Distinguishing Cause from Effect with Causal Velocity Models
67. ICML 2025Double Machine Learning for Causal Inference under Shared-State Interference
68. ICML 2025Explicit Discovery of Nonlinear Symmetries from Dynamic Data
69. ICML 2025Extracting Rare Dependence Patterns via Adaptive Sample Reweighting
70. ICML 2025Falsification of Unconfoundedness by Testing Independence of Causal Mechanisms
71. ICML 2025Federated Causal Structure Learning with Non-identical Variable Sets
72. ICML 2025Generating Hypotheses of Dynamic Causal Graphs in Neuroscience: Leveraging Generative Factor Models of Observed Time Series
73. ICML 2025Hierarchical Reinforcement Learning with Targeted Causal Interventions
74. ICML 2025IBCircuit: Towards Holistic Circuit Discovery with Information Bottleneck
75. ICML 2025Identification of Latent Confounders via Investigating the Tensor Ranks of the Nonlinear Observations
76. ICML 2025Identifying biological perturbation targets through causal differential networks
77. ICML 2025Identifying Causal Direction via Variational Bayesian Compression
78. ICML 2025Isolated Causal Effects of Natural Language
79. ICML 2025Latent Variable Causal Discovery under Selection Bias
80. ICML 2025Local Identifying Causal Relations in the Presence of Latent Variables
81. ICML 2025Neural Discovery in Mathematics: Do Machines Dream of Colored Planes?
82. ICML 2025Permutation-based Rank Test in the Presence of Discretization and Application in Causal Discovery with Mixed Data
83. ICML 2025Since Faithfulness Fails: The Performance Limits of Neural Causal Discovery
84. ICML 2025Sparse Causal Discovery with Generative Intervention for Unsupervised Graph Domain Adaptation
85. ICML 2025Strong and Weak Identifiability of Optimization-based Causal Discovery in Non-linear Additive Noise Models
86. ICML 2024Adaptive Online Experimental Design for Causal Discovery
87. ICML 2024Automated Statistical Model Discovery with Language Models
88. ICML 2024Bivariate Causal Discovery using Bayesian Model Selection
89. ICML 2024Causal Bandits: The Pareto Optimal Frontier of Adaptivity, a Reduction to Linear Bandits, and Limitations around Unknown Marginals
90. ICML 2024Causal Discovery via Conditional Independence Testing with Proxy Variables
91. ICML 2024Causal Discovery with Fewer Conditional Independence Tests
92. ICML 2024Causal Inference from Competing Treatments
93. ICML 2024Causal Representation Learning Made Identifiable by Grouping of Observational Variables
94. ICML 2024Challenges and Considerations in the Evaluation of Bayesian Causal Discovery
95. ICML 2024Collaborative Heterogeneous Causal Inference Beyond Meta-analysis
96. ICML 2024Discovering Mixtures of Structural Causal Models from Time Series Data
97. ICML 2024Enforcing Constraints in RNA Secondary Structure Predictions: A Post-Processing Framework Based on the Assignment Problem
98. ICML 2024Foundations of Testing for Finite-Sample Causal Discovery
99. ICML 2024How Transformers Learn Causal Structure with Gradient Descent
100. ICML 2024Intersectional Unfairness Discovery

常见问题

2023–2026 年四大会议一共有多少篇因果发现论文？

共 379 篇，按年份分别是 2023 年 59 篇、2024 年 82 篇、2025 年 99 篇、2026 年 139 篇。

NeurIPS 2026 有多少篇因果发现论文？

NeurIPS 2026 有 53 篇因果发现论文，上一届是 34 篇。

ICLR 2026 有多少篇因果发现论文？

ICLR 2026 有 25 篇因果发现论文，上一届是 27 篇。

ICML 2026 有多少篇因果发现论文？

ICML 2026 有 54 篇因果发现论文，上一届是 31 篇。

CVPR 2026 有多少篇因果发现论文？

CVPR 2026 有 7 篇因果发现论文，上一届是 7 篇。

哪个会议的因果发现论文最多？

NeurIPS，2023–2026 年共 150 篇。