AI RESEARCH
TFM-Retouche: A Lightweight Input-Space Adapter for Tabular Foundation Models
arXiv CS.LG
•
ArXi:2605.06047v1 Announce Type: new Tabular foundation models (TFMs), such as TabPFN-2.6, TabICLv2, ConTextTab, Mitra, LimiX, and TabDPT, achieve strong zero-shot performance through in-context learning, but their inductive biases remain fixed at inference time. Adapting a pretrained TFM to a specific dataset or task typically requires either full fine-tuning, which is computationally expensive, or parameter-efficient tuning methods (PEFT) such as LoRA, which must be tailored to the internal architecture of each.