AI RESEARCH
LUCoS: Latent Unsupervised Context Selection for Tabular Foundation Models
arXiv CS.AI
•
ArXi:2605.27254v1 Announce Type: cross Selecting which instances to label is a key challenge in low-label tabular learning. For recent Tabular Foundation Models such as TabPFN, context selection directly determines predictive performance. Supervised oracle experiments show that carefully chosen labeled context sets can strongly outperform random selection under the same labeling budget. However, the cold-start setting, where instances must be selected before any labels are available, has received little attention in the TFM literature. This problem is fundamentally geometric.