3 papers
cs.LG2026
Support-Compiled Feature Folding: More Evidence at Lower Memory Across Tabular Foundation Models
Tian Zhou, Beverly Jin, Xue Wang +6
Tabular foundation models face a feature-side scaling dilemma: full-width pairwise mixing grows quadratically with the number of columns, whereas feature selection saves memory by…
cs.LG2026
Transferable Evidence Reconstruction for Longitudinal Glucose Representations
Tian Zhou, Bingqing Peng, Linxiao Yang +6
Long physiological recordings contain many routine measurements, while predictive information is often concentrated in rare events, sustained burden, and recurring temporal pattern…
cs.LG2026
What Do Tabular Foundation Models Compute In Context? In-Situ Representation Refinement through Attention-Gated Updates
Tian Zhou, Beverly Jin, Linxiao Yang +6
What reusable computation should a tabular foundation model learn when every table defines a new supervised task? We develop in-situ representation refinement: support labels guide…