A transformer foundation model is trained on synthetic data from a novel prior over continuous-treatment data-generating processes to predict treatment-response curves via in-context learning without task-specific fine-tuning.
Causal data augmentation for robust fine-tuning of tabular foundation models.arXiv:2601.04110, 2026
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Causal Foundation Models with Continuous Treatments
A transformer foundation model is trained on synthetic data from a novel prior over continuous-treatment data-generating processes to predict treatment-response curves via in-context learning without task-specific fine-tuning.