Treatment Effect papers, 2023–2026

Key findings

• Treatment Effect went from 75 papers in 2023 to 106 in 2026, roughly 1.4x in three years.
• NeurIPS publishes the most Treatment Effect work: 131 papers from 2023 to 2026, 34% of the four-venue total.
• The fastest-growing overlap is with General ML · unsupervised and semisupervised learning: papers tagged with both rose from 3 in 2023 to 10 in 2026.
• Among the 5 topics under Causal and Fairness, it ranks #2 by 2026 paper count; the fastest grower in the group, Causal Discovery, is up 2.4x versus 1.4x here.

Representative papers

Spread across years and venues so every edition shows up

• 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

All Treatment Effect papers

31 papers, page 1 of 1

1. ICML 2025A Meta-learner for Heterogeneous Effects in Difference-in-Differences
2. ICML 2025A Unified View on Learning Unnormalized Distributions via Noise-Contrastive Estimation
3. ICML 2025Active Treatment Effect Estimation via Limited Samples
4. ICML 2025Adjustment for Confounding using Pre-Trained Representations
5. ICML 2025AutoCATE: End-to-End, Automated Treatment Effect Estimation
6. ICML 2025Causal Effect Identification in lvLiNGAM from Higher-Order Cumulants
7. ICML 2025Counterfactual Contrastive Learning with Normalizing Flows for Robust Treatment Effect Estimation
8. ICML 2025Data-driven Design of Randomized Control Trials with Guaranteed Treatment Effects
9. ICML 2025Density Ratio Estimation with Conditional Probability Paths
10. ICML 2025Dequantified Diffusion-Schrödinger Bridge for Density Ratio Estimation
11. ICML 2025Distinguishing Cause from Effect with Causal Velocity Models
12. ICML 2025Doubly Robust Conformalized Survival Analysis with Right-Censored Data
13. ICML 2025Enhancing Treatment Effect Estimation via Active Learning: A Counterfactual Covering Perspective
14. ICML 2025Generalizing Causal Effects from Randomized Controlled Trials to Target Populations across Diverse Environments
15. ICML 2025Heterogeneous Treatment Effect in Time-to-Event Outcomes: Harnessing Censored Data with Recursively Imputed Trees
16. ICML 2025Learning Joint Interventional Effects from Single-Variable Interventions in Additive Models
17. ICML 2025Learning Representations of Instruments for Partial Identification of Treatment Effects
18. ICML 2025Measuring Variable Importance in Heterogeneous Treatment Effects with Confidence
19. ICML 2025On Efficient Estimation of Distributional Treatment Effects under Covariate-Adaptive Randomization
20. ICML 2025On Fine-Grained Distinct Element Estimation
21. ICML 2025Optimistic Algorithms for Adaptive Estimation of the Average Treatment Effect
22. ICML 2025PertEval-scFM: Benchmarking Single-Cell Foundation Models for Perturbation Effect Prediction
23. ICML 2025Quantifying Treatment Effects: Estimating Risk Ratios via Observational Studies
24. ICML 2025Reducing Confounding Bias without Data Splitting for Causal Inference via Optimal Transport
25. ICML 2025Sample Complexity of Branch-length Estimation by Maximum Likelihood
26. ICML 2025Strategic A/B testing via Maximum Probability-driven Two-armed Bandit
27. ICML 2025Stronger Neyman Regret Guarantees for Adaptive Experimental Design
28. ICML 2025The Butterfly Effect: Neural Network Training Trajectories Are Highly Sensitive to Initial Conditions
29. ICML 2025The Double-Ellipsoid Geometry of CLIP
30. ICML 2025Transformer-Based Spatial-Temporal Counterfactual Outcomes Estimation
31. ICML 2025Uniform Mean Estimation for Heavy-Tailed Distributions via Median-of-Means

FAQ

How many Treatment Effect papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

385 in total: 75 in 2023, 106 in 2024, 98 in 2025, 106 in 2026.

How many Treatment Effect papers are at NeurIPS 2026?

NeurIPS 2026 has 44 Treatment Effect papers, versus 34 the year before.

How many Treatment Effect papers are at ICLR 2026?

ICLR 2026 has 18 Treatment Effect papers, versus 16 the year before.

How many Treatment Effect papers are at ICML 2026?

ICML 2026 has 27 Treatment Effect papers, versus 31 the year before.

How many Treatment Effect papers are at CVPR 2026?

CVPR 2026 has 17 Treatment Effect papers, versus 17 the year before.

Which conference publishes the most Treatment Effect papers?

NeurIPS, with 131 papers from 2023 to 2026.