Causal Foundation Models
cs.LG, stat.ML
Submitted: 2026-09-02
Updated: 2026-09-02
Code: https://github.com/layer6ai-labs/cfms
Terminology
Sources
- IV-ICL: Bounding Causal Effects with Instrumental Variables via In-Context Learning
- FoundCause: Causal Discovery with Latent Confounders from Observational Data
- Black Box Causal Inference: Effect Estimation via Meta Prediction
- SurvPFN: Towards Foundation Models for Survival Predictions
- DAG-FM: A Foundation Model for Causal Discovery under Heterogeneous Causal Mechanisms
- PerturbPFN: Probing the Limits of Synthetic Priors in Drug Perturbation Modelling
- Real-TabPFN: Improving Tabular Foundation Models via Continued Pre-training With Real-World Data
- TabPFN-3: Technical Report
- DCD-PFN: A Decoupling-Aware Foundation Model for Causal Discovery
- Advancing Open and Reproducible Relational Learning: RelArena- alpha, TabPFN-Rel and RPI
- TabDPT-Turbo: Efficient In-Context Learning for Tabular Prediction
- Amortizing Causal Sensitivity Analysis via Prior Data-Fitted Networks
- Tabular Foundation Models Can Do Survival Analysis
- TabCausal: Pretraining Across Causal Environments for Tabular Causal Discovery
- Prior-Data Fitted Networks for Causal Inference: a Simulation Study with Real-World Scenarios
- RealCause: Realistic Causal Inference Benchmarking
- SurvivalPFN: Amortizing Survival Prediction via In-Context Bayesian Inference
- CDFM: Towards a General-Purpose Causal Discovery Foundation Model
- Survival In-Context: Amortized Bayesian Survival Analysis via Prior-Fitted Networks
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks