mlsanityData to 14 Oct 2026

Causal Foundation Models

arXiv 2609.03003 ↗First posted 2 Sep 2026cs.LG stat.MLcited by 1

Not on the map. Why?

Abstract (arXiv)

Causal inference is the practice of estimating the effect of a treatment or intervention from data. It traditionally requires a bespoke pipeline for every new problem: first proposing a causal mechanism, selecting a compatible estimator, and finally training it. Meanwhile, across diverse settings and modalities, much of machine learning has shifted to the paradigm of foundation models: networks pretrained once at scale and applied to new tasks without fine-tuning. Causal foundation models (CFMs) bring this paradigm to causal inference. CFMs are pretrained neural networks that estimate causal quantities, such as the average treatment effect, on entirely new datasets using in-context learning without requiring model updates. This work provides a practical introduction to this emerging area. We summarize the necessary background in causal inference and machine learning before discussing CFMs. Throughout, we include example code and Jupyter notebooks.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 66 of its 108 references that are in the map. First posted on arXiv 2 Sep 2026.

Builds on

66 of 108 references.

References · 66

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  4. 2022TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Secondcited by 674
  5. 2015Estimation and Inference of Heterogeneous Treatment Effects using Random Forestscited by 600
  6. 2017Meta-learners for Estimating Heterogeneous Treatment Effects using Machine Learningcited by 478
  7. 2021Transformers Can Do Bayesian Inferencecited by 360
  8. 2025TabICL: A Tabular Foundation Model for In-Context Learning on Large Datacited by 289
  9. 2020A Survey on Causal Inferencecited by 202
  10. 2017Bayesian Inference of Individualized Treatment Effects using Multi-task Gaussian Processescited by 158
  11. 2026TabICLv2: A better, faster, scalable, and open tabular foundation modelcited by 144
  12. 2024TabDPT: Scaling Tabular Foundation Models on Real Datacited by 113
38 more
  1. 2019FLAML: A Fast and Lightweight AutoML Librarycited by 106
  2. 2023ForecastPFN: Synthetically-Trained Zero-Shot Forecastingcited by 104
  3. 2019Learning Counterfactual Representations for Estimating Individual Dose-Response Curvescited by 90
  4. 2022Amortized Inference for Causal Structure Learningcited by 90
  5. 2025Mitra: Mixed Synthetic Priors for Enhancing Tabular Foundation Modelscited by 77
  6. 2022Learning to Induce Causal Structurecited by 68
  7. 2023A Survey on Causal Discovery: Theory and Practicecited by 63
  8. 2025Do-PFN: In-Context Learning for Causal Effect Estimationcited by 51
  9. 2025CausalPFN: Amortized Causal Effect Estimation via In-Context Learningcited by 49
  10. 2020RealCause: Realistic Causal Inference Benchmarkingcited by 46
  11. 2016The State of Applied Econometrics - Causality and Policy Evaluationcited by 41
  12. 2025Real-TabPFN: Improving Tabular Foundation Models via Continued Pre-training With Real-World Datacited by 41
  13. 2025ConTextTab: A Semantics-Aware Tabular In-Context Learnercited by 34
  14. 2025Foundation Models for Causal Inference via Prior-Data Fitted Networkscited by 32
  15. 2025TimePFN: Effective Multivariate Time Series Forecasting with Synthetic Datacited by 29
  16. 2022Empirical Analysis of Model Selection for Heterogeneous Causal Effect Estimationcited by 25
  17. 2024A Meta-Learning Approach to Bayesian Causal Discoverycited by 22
  18. 2024Sample, estimate, aggregate: A recipe for causal discovery foundation modelscited by 21
  19. 2023Zero-shot causal learningcited by 17
  20. 2023Towards Causal Foundation Model: on Duality between Causal Inference and Attentioncited by 17
  21. 2026Relational In-Context Learning via Synthetic Pre-training with Structural Priorcited by 14
  22. 2025Black Box Causal Inference: Effect Estimation via Meta Predictioncited by 13
  23. 2025Estimating Interventional Distributions with Uncertain Causal Graphs through Meta-Learningcited by 13
  24. 2024Demystifying amortized causal discovery with transformerscited by 11
  25. 2024Doubly robust inference via calibrationcited by 9
  26. 2026Tabular Foundation Models Can Do Survival Analysiscited by 9
  27. 2024Marginal Causal Flows for Validation and Inferencecited by 8
  28. 2026Use What You Know: Causal Foundation Models with Partial Graphscited by 7
  29. 2026Interventional Time Series Priors for Causal Foundation Modelscited by 7
  30. 2026Survival In-Context: Amortized Bayesian Survival Analysis via Prior-Fitted Networkscited by 6
  31. 2026TabDPT-Turbo: Efficient In-Context Learning for Tabular Predictioncited by 6
  32. 2026Arrow: A Foundation Model for Causal Discoverycited by 5
  33. 2025Learning Causal Graphs at Scale: A Foundation Model Approachcited by 4
  34. 2026Frequentist Consistency of Prior-Data Fitted Networks for Causal Inferencecited by 4
  35. 2026Causal Foundation Models with Continuous Treatmentscited by 4
  36. 2026Towards Continuous-time Causal Foundation Modelscited by 4
  37. 2026TabCausal: Pretraining Across Causal Environments for Tabular Causal Discoverycited by 4
  38. 2026SurvPFN: Towards Foundation Models for Survival Predictionscited by 4

50 most cited of 66 All 66 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026ProximalFM: Amortized Proximal Causal Inference under Hidden Confoundingcited by 0