DAG-FM: A Foundation Model for Causal Discovery Under Heterogeneous Mechanisms

Jul 14, 2026

Researchers introduce DAG-FM, a novel foundation model for causal discovery that decomposes the process into two auto-regressive stages using specialized Transformer-based modules. The model incorporates a Mixture-of-Leaf-Experts approach to adapt to diverse causal mechanisms and demonstrates state-of-the-art performance on both synthetic and real-world datasets, outperforming existing classical and foundation model approaches.

Why it matters: This work represents a significant advance in scalable causal discovery, enabling more accurate inference of cause-effect relationships from complex observational data.

Full story at: arXiv Statistical ML ↗