深度学习 · causal inference论文趋势 2023–2026

主要结论

• 深度学习 · causal inference论文从 2023 年的 108 篇降到 2026 年的 66 篇，热度在回落。
• NeurIPS 是发深度学习 · causal inference论文最多的会议，2023–2026 年共 196 篇，占四个会议总量的 62%。
• 交叉方向里涨得最快的是因果推荐：同时属于两个主题的论文从 2023 年的 27 篇增至 2026 年的 55 篇。
• 在「深度学习」的 11 个主题里，它的 2026 年论文数排第 10；同组增长最快的扩散模型是 4.1 倍，深度学习 · causal inference是 0.6 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 2026From Groups to Rings: Causal Evidence for Algebraic Decomposition in Grokked Transformers
• ICML 2026Towards a Holistic Understanding of Selection Bias for Causal Effect Identification
• ICLR 2026Causal-Steer: Disentangled Continuous Style Control without Parallel Corpora
• CVPR 2026Breaking Spurious Correlations Uncertainty-Driven Causal Transformers for AU Detection
• NeurIPS 2025CCL: Causal-aware In-context Learning for Out-of-Distribution Generalization
• ICML 2025Position: Probabilistic Modelling is Sufficient for Causal Inference
• ICLR 2025Robust Root Cause Diagnosis using In-Distribution Interventions
• CVPR 2025Image Quality Assessment: Investigating Causal Perceptual Effects with Abductive Counterfactual Inference
• NeurIPS 2024A Non-parametric Direct Learning Approach to Heterogeneous Treatment Effect Estimation under Unmeasured Confounding
• ICML 2024Collaborative Heterogeneous Causal Inference Beyond Meta-analysis
• ICLR 2024Causal-StoNet: Causal Inference for High-Dimensional Complex Data
• CVPR 2024Bi-Causal: Group Activity Recognition via Bidirectional Causality
• NeurIPS 2023A Cross-Moment Approach for Causal Effect Estimation
• ICML 2023Proximal Causal Learning of Conditional Average Treatment Effects
• ICLR 2023GEASS: Neural causal feature selection for high-dimensional biological data
• CVPR 2023CafeBoost: Causal Feature Boost To Eliminate Task-Induced Bias for Class Incremental Learning
• NeurIPS 2026A Characterization of Latent Variable Causal Models Consistent with Observational Data
• ICML 2026Caracal: Causal Architecture via Spectral Mixing
• ICLR 2026Counterfactual Structural Causal Bandits
• CVPR 2026Bridge Basis-Driven Causal Inference Marries VFMs for Domain Generalization

全部深度学习 · causal inference论文

共 196 篇，第 1 / 4 页

1. NeurIPS 2026A Characterization of Latent Variable Causal Models Consistent with Observational Data
2. NeurIPS 2026A Faster Algorithm for the Half-Trek Criterion in Structural Causal Models
3. NeurIPS 2026CAST: Causal Anchored Simplex Transport for Distribution-Valued Time Series
4. NeurIPS 2026Causal Abstractions, Categorically Unified
5. NeurIPS 2026Causal Effect Identification with a Single Agnostic Proxy
6. NeurIPS 2026Causal Gradient Steering: Exposing Shortcut Gradients by Destroying Causal Signal
7. NeurIPS 2026Causal learning with the invariance principle
8. NeurIPS 2026Causal Survival Forests with Negative Controls
9. NeurIPS 2026Characterizing Underrepresentation in Generalizing Causal Survival Estimates
10. NeurIPS 2026Confounding-Aware Client Selection in Federated Learning via Causal Mediation Analysis
11. NeurIPS 2026Decision Path Tracing for Causal Analysis in Transformers
12. NeurIPS 2026Decomposing Effects in Neural Causal Models
13. NeurIPS 2026DoAtlas-1: A Causal Compilation Paradigm for Clinical AI
14. NeurIPS 2026From Groups to Rings: Causal Evidence for Algebraic Decomposition in Grokked Transformers
15. NeurIPS 2026Generalized Bayes for Causal Inference
16. NeurIPS 2026Improving Causal Explanations
17. NeurIPS 2026Learning Contextual Causal Dynamics for Robust Exploration in Reinforcement Learning
18. NeurIPS 2026Learning Deployable Causal Action Geometry under Temporal Non-Stationarity
19. NeurIPS 2026Neural Causal Models under Markov Equivalence
20. NeurIPS 2026Online Causal Configuration for Networked Systems via Doubly Robust Steady-State Learning
21. NeurIPS 2026Revealing Epistemic Uncertainty in MLLMs via Causal-Invariant Masking
22. NeurIPS 2026Statistical Inference in Causal Partial Identification under Smooth Densities
23. NeurIPS 2026Structural Causal Bottleneck Models
24. NeurIPS 2026Towards a Universal Causal Reasoner
25. NeurIPS 2026Two-Clustering Regime of Token Dynamics in Causal Attention
26. NeurIPS 2026Who caused $Y$? Local identifiability for learning causal parents
27. NeurIPS 2026Why Are LLMs Confidently Wrong? Correcting Overconfident Errors via Causal Head Intervention
28. NeurIPS 2026xWhy: Causal Learning from Explanations
29. NeurIPS 2025A Cautionary Tale on Integrating Studies with Disparate Outcome Measures for Causal Inference
30. NeurIPS 2025CCL: Causal-aware In-context Learning for Out-of-Distribution Generalization
31. NeurIPS 2025Data Fusion for Partial Identification of Causal Effects
32. NeurIPS 2025Decoding Causal Structure: End-to-End Mediation Pathways Inference
33. NeurIPS 2025Density Ratio-Free Doubly Robust Proxy Causal Learning
34. NeurIPS 2025Do-PFN: In-Context Learning for Causal Effect Estimation
35. NeurIPS 2025Prediction-Powered Causal Inferences
36. NeurIPS 2025Relaxing partition admissibility in Cluster-DAGs: a causal calculus with arbitrary variable clustering
37. NeurIPS 2025Structural Causal Bandits under Markov Equivalence
38. NeurIPS 2024A Non-parametric Direct Learning Approach to Heterogeneous Treatment Effect Estimation under Unmeasured Confounding
39. NeurIPS 2024A Simple yet Scalable Granger Causal Structural Learning Approach for Topological Event Sequences
40. NeurIPS 2024Achievable distributional robustness when the robust risk is only partially identified
41. NeurIPS 2024An effective framework for estimating individualized treatment rules
42. NeurIPS 2024Automated Efficient Estimation using Monte Carlo Efficient Influence Functions
43. NeurIPS 2024Causal Bandits for Linear Structural Equation Models
44. NeurIPS 2024Causal Contrastive Learning for Counterfactual Regression Over Time
45. NeurIPS 2024Causal Dependence Plots
46. NeurIPS 2024Causal Discovery from Event Sequences by Local Cause-Effect Attribution
47. NeurIPS 2024Causal discovery with endogenous context variables
48. NeurIPS 2024Causal Effect Identification in a Sub-Population with Latent Variables
49. NeurIPS 2024Causal Imitation for Markov Decision Processes: a Partial Identification Approach
50. NeurIPS 2024Causal Inference in the Closed-Loop: Marginal Structural Models for Sequential Excursion Effects

常见问题

2023–2026 年四大会议一共有多少篇深度学习 · causal inference论文？

共 316 篇，按年份分别是 2023 年 108 篇、2024 年 108 篇、2025 年 34 篇、2026 年 66 篇。

NeurIPS 2026 有多少篇深度学习 · causal inference论文？

NeurIPS 2026 有 28 篇深度学习 · causal inference论文，上一届是 9 篇。

ICLR 2026 有多少篇深度学习 · causal inference论文？

ICLR 2026 有 8 篇深度学习 · causal inference论文，上一届是 6 篇。

ICML 2026 有多少篇深度学习 · causal inference论文？

ICML 2026 有 26 篇深度学习 · causal inference论文，上一届是 18 篇。

CVPR 2026 有多少篇深度学习 · causal inference论文？

CVPR 2026 有 4 篇深度学习 · causal inference论文，上一届是 1 篇。

哪个会议的深度学习 · causal inference论文最多？

NeurIPS，2023–2026 年共 196 篇。