Causal Foundation Models

Hugging Face Daily Papers Papers
causal-inference foundation-models in-context-learning machine-learning neural-networks causal-effects

Summary

This paper introduces Causal Foundation Models, which use pretrained neural networks to estimate causal effects on new datasets via in-context learning without fine-tuning, providing a practical guide to this emerging field.

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.
Original Article
View Cached Full Text

Cached at: 09/08/26, 04:25 PM

Paper page - Causal Foundation Models

Source: https://huggingface.co/papers/2609.03003

Abstract

Causal foundation models apply pretrained neural networks to estimate causal effects on new datasets via in-context learning without fine-tuning.

Causal inferenceis 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 tocausal inference. CFMs arepretrained neural networksthat estimate causal quantities, such as theaverage treatment effect, on entirely new datasets usingin-context learningwithout requiring model updates. This work provides a practical introduction to this emerging area. We summarize the necessary background incausal inferenceand machine learning before discussing CFMs. Throughout, we include example code and Jupyter notebooks.

View arXiv pageView PDFGitHub10Add to collection

Get this paper in your agent:

hf papers read 2609\.03003

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2609.03003 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2609.03003 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2609.03003 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

Causal Foundation Models

arXiv cs.LG

This paper introduces causal foundation models (CFMs), which are pretrained neural networks that estimate causal quantities on new datasets using in-context learning without requiring fine-tuning.

Generalized Multimodal Foundation Model

arXiv cs.LG

This paper introduces a generalized multimodal foundation model capable of handling arbitrary modality combinations and prediction tasks, achieving competitive performance through training on large-scale synthetic datasets with diverse causal structures.

Towards Continuous-time Causal Foundation Models

arXiv cs.LG

Proposes a continuity criterion for extending discrete-time causal prior-data fitted networks to continuous time using stochastic differential equations, introducing a taxonomy and fine-grid integration method that outperforms naive integration on irregular observation schedules.

Causal Discovery in the Era of Agents

Hugging Face Daily Papers

This paper argues that language model agents should assist causal discovery workflows by providing contextual support and explanations rather than generating causal conclusions, and introduces causal-learn+ platform to demonstrate this principle.