← Back to all news
arXiv Machine Learning By Christopher Stith, Hossein Rahmani, Jesse C. Cresswell

Causal Foundation Models

Read the original on arXiv Machine Learning →

Causal Foundation Models (CFMs) are pretrained neural networks designed to estimate causal quantities—such as the average treatment effect—across new datasets using in‑context learning, eliminating the need for bespoke pipelines or model updates. The paper introduces CFMs, reviews foundational concepts in causal inference and machine learning, and provides practical code examples and Jupyter notebooks to illustrate their application.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Machine Learning
Jun 26

Use What You Know: Causal Foundation Models with Partial Graphs

arXiv:2602. 14972v2 Announce Type: replace Abstract: Estimating causal quantities traditionally relies on bespoke estimators tailored to specific assumptions.

By Arik Reuter, Anish Dhir, Cristiana Diaconu, Jake Robertson, Ole Ossen, Frank Hutter, Adrian Weller, Mark van der Wilk, Bernhard Sch\"olkopf
More like this →
arXiv Machine Learning
Aug 4

Large Causal Models for Temporal Causal Discovery

arXiv:2602. 18662v2 Announce Type: replace Abstract: Causal discovery for both cross-sectional and temporal data has traditionally followed a dataset-specific paradigm, where a new model is fitted for each individual dataset.

By Nikolaos Kougioulis, Nikolaos Gkorgkolis, MingXue Wang, Bora Caglayan, Dario Simionato, Andrea Tonon, Ioannis Tsamardinos
benchmarks
More like this →
arXiv AI
Aug 20

CausalProfiler: Generating Synthetic Benchmarks for Rigorous and Transparent Evaluation of Causal Machine Learning

CausalProfiler is a synthetic benchmark generator designed to evaluate causal machine learning (Causal ML) methods more rigorously and transparently. It randomly samples causal models, data, queries, and ground truths based on explicit design choices across observation, intervention, and counterfactual reasoning levels, providing coverage guarantees and transparent assumptions. The authors demonstrate its utility by testing several state‑of‑the‑art methods under diverse conditions, both within and outside the identification regime, highlighting the insights CausalProfiler can reveal.

By Panayiotis Panayiotou, Audrey Poinsot, Alessandro Leite, Nicolas Chesneau, Marc Schoenauer, \"Ozg\"ur \c{S}im\c{s}ek
benchmarks
More like this →