Реклама

GEAR: Generative Expansion and Real Anchoring for Two-Stage Distillation of Tabular Foundation Models

#GEAR #Generative #Expansion #Real #Anchoring

arXiv:2608.18849v1 Announce Type: cross Abstract: Tabular foundation models (TFMs) achieve strong performance through in-context learning, but context-dependent inference imposes substantial latency and memory costs, hindering large-scale deployment. We propose GEAR (\emph{Generative Expansion and…