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 379 篇，第 6 / 8 页

251. ICLR 2024Robust agents learn causal world models
252. ICLR 2024Structural Estimation of Partially Observed Linear Non-Gaussian Acyclic Model: A Practical Approach with Identifiability
253. ICML 2024Adaptive Online Experimental Design for Causal Discovery
254. ICML 2024Automated Statistical Model Discovery with Language Models
255. ICML 2024Bivariate Causal Discovery using Bayesian Model Selection
256. ICML 2024Causal Bandits: The Pareto Optimal Frontier of Adaptivity, a Reduction to Linear Bandits, and Limitations around Unknown Marginals
257. ICML 2024Causal Discovery via Conditional Independence Testing with Proxy Variables
258. ICML 2024Causal Discovery with Fewer Conditional Independence Tests
259. ICML 2024Causal Inference from Competing Treatments
260. ICML 2024Causal Representation Learning Made Identifiable by Grouping of Observational Variables
261. ICML 2024Challenges and Considerations in the Evaluation of Bayesian Causal Discovery
262. ICML 2024Collaborative Heterogeneous Causal Inference Beyond Meta-analysis
263. ICML 2024Discovering Mixtures of Structural Causal Models from Time Series Data
264. ICML 2024Enforcing Constraints in RNA Secondary Structure Predictions: A Post-Processing Framework Based on the Assignment Problem
265. ICML 2024Foundations of Testing for Finite-Sample Causal Discovery
266. ICML 2024How Transformers Learn Causal Structure with Gradient Descent
267. ICML 2024Intersectional Unfairness Discovery
268. ICML 2024Learning Causal Dynamics Models in Object-Oriented Environments
269. ICML 2024Learning Causal Relations from Subsampled Time Series with Two Time-Slices
270. ICML 2024Local Causal Structure Learning in the Presence of Latent Variables
271. ICML 2024Modular Learning of Deep Causal Generative Models for High-dimensional Causal Inference
272. ICML 2024On Positivity Condition for Causal Inference
273. ICML 2024On the Recoverability of Causal Relations from Temporally Aggregated I.I.D. Data
274. ICML 2024On the sample complexity of conditional independence testing with Von Mises estimator with application to causal discovery
275. ICML 2024Optimal Kernel Choice for Score Function-based Causal Discovery
276. ICML 2024Optimal Transport for Structure Learning Under Missing Data
277. ICML 2024Reducing Balancing Error for Causal Inference via Optimal Transport
278. ICML 2024Scalable and Flexible Causal Discovery with an Efficient Test for Adjacency
279. ICML 2024Score-Based Causal Discovery of Latent Variable Causal Models
280. ICML 2024Stable Differentiable Causal Discovery
281. ICML 2024StableMask: Refining Causal Masking in Decoder-only Transformer
282. ICML 2024Tight Partial Identification of Causal Effects with Marginal Distribution of Unmeasured Confounders
283. ICML 2024Transport of Algebraic Structure to Latent Embeddings
284. ICML 2024Which Frequencies do CNNs Need? Emergent Bottleneck Structure in Feature Learning
285. NeurIPS 2024A Simple yet Scalable Granger Causal Structural Learning Approach for Topological Event Sequences
286. NeurIPS 2024Amortized Active Causal Induction with Deep Reinforcement Learning
287. NeurIPS 2024Causal Bandits for Linear Structural Equation Models
288. NeurIPS 2024Causal Discovery from Event Sequences by Local Cause-Effect Attribution
289. NeurIPS 2024Causal discovery with endogenous context variables
290. NeurIPS 2024Causal vs. Anticausal merging of predictors
291. NeurIPS 2024Causal-learn: Causal Discovery in Python
292. NeurIPS 2024CausalStock: Deep End-to-end Causal Discovery for News-driven Multi-stock Movement Prediction
293. NeurIPS 2024ChronoEpilogi: Scalable Time Series Selection with Multiple Solutions
294. NeurIPS 2024Clustering in Causal Attention Masking
295. NeurIPS 2024Differentiable Structure Learning with Partial Orders
296. NeurIPS 2024Discovery of the Hidden World with Large Language Models
297. NeurIPS 2024Do causal predictors generalize better to new domains?
298. NeurIPS 2024Do Finetti: On Causal Effects for Exchangeable Data
299. NeurIPS 2024Graph Structure Inference with BAM: Neural Dependency Processing via Bilinear Attention
300. NeurIPS 2024Hybrid Top-Down Global Causal Discovery with Local Search for Linear and Nonlinear Additive Noise Models

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。