Test-Time Compute for Tabular Foundation Models: Mechanisms, Gains, and Limits
Which forms of test-time compute improve the predictions of strong pretrained tabular foundation models (TFMs)? We systematically study this along three axes: adaptation, aggregation, and context construction. Our evaluation spans modern TFMs across the TabArena benchmark, supplemented by experiments on wide and large-...
Kang-Hui Ning, Marin Bilos, James T. Wilson et al.
· 0 citations