AI RESEARCH
Active In-Context Learning for Tabular Foundation Models
arXiv CS.LG
•
ArXi:2603.27385v1 Announce Type: new Active learning (AL) reduces labeling cost by querying informative samples, but in tabular settings its cold-start gains are often limited because uncertainty estimates are unreliable when models are trained on very few labels. Tabular foundation models such as TabPFN provide calibrated probabilistic predictions via in-context learning (ICL), i.e., without task-specific weight updates, enabling an AL regime in which the labeled context - rather than parameters - is iteratively optimized.