2026
Is One Layer Enough? Understanding Inference Dynamics in Tabular Foundation Models
ICML 2026poster
Transformer-based tabular foundation models (TFMs) dominate small to medium tabular predictive benchmark tasks, yet their inference mechanisms remain largely unexplored. We present the first large-scale mechanistic study of layerwise dynamics in 6 state-of-the-art tabular in-context learning models.…