处理效应论文趋势 2023–2026

主要结论

• 处理效应论文从 2023 年的 75 篇增长到 2026 年的 106 篇，三年间扩大到约 1.4 倍。
• NeurIPS 是发处理效应论文最多的会议，2023–2026 年共 131 篇，占四个会议总量的 34%。
• 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 2；同组增长最快的因果发现是 2.4 倍，处理效应是 1.4 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 2026Assessing the robustness of heterogeneous treatment effects in survival analysis under informative censoring
• ICML 2026Causal Effect Identifiability in the Presence of Latent Confounders Without Auxiliary Variables
• ICLR 2026ActiveCQ: Active Estimation of Causal Quantities
• CVPR 2026Event Stream Filtering via Probability Flux Estimation
• NeurIPS 2025Born a Transformer -- Always a Transformer? On the Effect of Pretraining on Architectural Abilities
• ICML 2025A Meta-learner for Heterogeneous Effects in Difference-in-Differences
• ICLR 2025Causal Effect Estimation with Mixed Latent Confounders and Post-treatment Variables
• CVPR 2025Any6D: Model-free 6D Pose Estimation of Novel Objects
• NeurIPS 2024Benchmarking Estimators for Natural Experiments: A Novel Dataset and a Doubly Robust Algorithm
• ICML 2024A Generative Approach for Treatment Effect Estimation under Collider Bias: From an Out-of-Distribution Perspective
• ICLR 2024A Variational Framework for Estimating Continuous Treatment Effects with Measurement Error
• CVPR 2024LightOctree: Lightweight 3D Spatially-Coherent Indoor Lighting Estimation
• NeurIPS 2023An Efficient Doubly-Robust Test for the Kernel Treatment Effect
• ICML 2023A Three-regime Model of Network Pruning
• ICLR 2023Causal Estimation for Text Data with (Apparent) Overlap Violations
• CVPR 2023HRDFuse: Monocular 360deg Depth Estimation by Collaboratively Learning Holistic-With-Regional Depth Distributions
• NeurIPS 2026Automated Causal Effect Estimation through Self-Evolving AI
• ICML 2026Causal-EPIG: Causally Aligned Active CATE Estimation
• ICLR 2026Foundation Models for Causal Inference via Prior-Data Fitted Networks
• CVPR 2026The Invisible Gorilla Effect in Out-of-distribution Detection

全部处理效应论文

共 106 篇，第 1 / 3 页

1. CVPR 2026ACE-Merging Data-Free Model Merging with Adaptive Covariance Estimation
2. CVPR 2026Enhancing Accuracy of Uncertainty Estimation in Appearance-based Gaze Tracking with
3. CVPR 2026Enhancing Hands in 3D Whole-Body Pose Estimation with Conditional Hands
4. CVPR 2026Event Stream Filtering via Probability Flux Estimation
5. CVPR 2026Exploring 6D Object Pose Estimation with Deformation
6. CVPR 2026Gaze Target Estimation Anywhere with Concepts
7. CVPR 2026Iris Integrating Language into Diffusion-based Monocular Depth Estimation
8. CVPR 2026Lighting in Motion Spatiotemporal HDR Lighting Estimation
9. CVPR 2026Linear Fundamental Matrix Estimation from 7 or 5 Points
10. CVPR 2026Object-WIPER Training-Free Object and Associated Effect Removal in Videos
11. CVPR 2026PTC-Depth Pose-Refined Monocular Depth Estimation with Temporal Consistency
12. CVPR 2026RoSAMDepth Robust Self-supervised Depth Estimation Leveraging Segment Anything Model
13. CVPR 2026SCAPO Self-Supervised Category-Level Articulated Pose Estimation from a Single 3D
14. CVPR 2026The Drift Kernel Why Diffusion Models Change Even When Told
15. CVPR 2026The Invisible Gorilla Effect in Out-of-distribution Detection
16. CVPR 2026Towards Generalized Multimodal Homography Estimation
17. CVPR 2026Unsupervised 3d Motion Estimation Using Event Camera
18. ICLR 2026A Relative Error-Based Evaluation Framework of Heterogeneous Treatment Effect Estimators
19. ICLR 2026ActiveCQ: Active Estimation of Causal Quantities
20. ICLR 2026Direct Doubly Robust Estimation of Conditional Quantile Contrasts
21. ICLR 2026Foundation Models for Causal Inference via Prior-Data Fitted Networks
22. ICLR 2026Good allocations from bad estimates
23. ICLR 2026Heterogeneous Front-Door Effects: Debiased Estimation with Quasi-Oracle Guarantees
24. ICLR 2026IGC-Net for conditional average potential outcome estimation over time
25. ICLR 2026Matching without Group Barrier for Heterogeneous Treatment Effect Estimation
26. ICLR 2026Modeling Interference for Treatment Effect Estimation in Network Dynamic Environment
27. ICLR 2026NIMO: a Nonlinear Interpretable MOdel
28. ICLR 2026On the Interpolation Effect of Score Smoothing in Diffusion Models
29. ICLR 2026Overlap-Adaptive Regularization for Conditional Average Treatment Effect Estimation
30. ICLR 2026Overlap-weighted orthogonal meta-learner for treatment effect estimation over time
31. ICLR 2026RESA: Bringing Back What Sparse Attention Ignores with Residual Estimation
32. ICLR 2026Revenue Maximization Under Sequential Price Competition Via The Estimation Of $s$-Concave Demand Functions
33. ICLR 2026SurvHTE-Bench: A Benchmark for Heterogeneous Treatment Effect Estimation in Survival Analysis
34. ICLR 2026The Effect of Attention Head Count on Transformer Approximation
35. ICLR 2026The Matthew Effect of AI Programming Assistants: A Hidden Bias in Software Evolution
36. ICML 2026Bilinear Bandits with Partially Observable Features
37. ICML 2026Budgeted Active Experimentation for Treatment Effect Estimation from Observational and Randomized Data
38. ICML 2026Causal Effect Identifiability in the Presence of Latent Confounders Without Auxiliary Variables
39. ICML 2026Causal-EPIG: Causally Aligned Active CATE Estimation
40. ICML 2026Conditional Distributional Treatment Effects: Doubly Robust Estimation and Testing
41. ICML 2026DeepBlip: Estimating Conditional Average Treatment Effects Over Time
42. ICML 2026Doubly Robust Distributionally Robust Offline Contextual Pricing
43. ICML 2026Estimating Continuous Treatment Effects with Two-Stage Kernel Ridge Regression
44. ICML 2026Estimation of Treatment Effects Under Nonstationarity via the Truncated Policy Gradient Estimator
45. ICML 2026Even Faster Kernel Matrix Linear Algebra via Density Estimation
46. ICML 2026Feasible Fusion: Constrained Joint Estimation under Structural Non-Overlap
47. ICML 2026Frequentist Consistency of Prior-Data Fitted Networks for Causal Inference
48. ICML 2026Gaussian Mean Field Variational Inference can Overestimate Predictive Variance
49. ICML 2026Gradient-Based Causal Tree Ensembles: A Backbone Architecture for Heterogeneous Treatment Effects
50. ICML 2026Improved Distribution Estimation in $\ell_\infty$

常见问题

2023–2026 年四大会议一共有多少篇处理效应论文？

共 385 篇，按年份分别是 2023 年 75 篇、2024 年 106 篇、2025 年 98 篇、2026 年 106 篇。

NeurIPS 2026 有多少篇处理效应论文？

NeurIPS 2026 有 44 篇处理效应论文，上一届是 34 篇。

ICLR 2026 有多少篇处理效应论文？

ICLR 2026 有 18 篇处理效应论文，上一届是 16 篇。

ICML 2026 有多少篇处理效应论文？

ICML 2026 有 27 篇处理效应论文，上一届是 31 篇。

CVPR 2026 有多少篇处理效应论文？

CVPR 2026 有 17 篇处理效应论文，上一届是 17 篇。

哪个会议的处理效应论文最多？

NeurIPS，2023–2026 年共 131 篇。