TAFFY: A Task-Adaptive Tabular Foundation Model with In-Context Diversity

Excerpt

arXiv:2610.07559v1 Announce Type: new Abstract: Recent progress in tabular foundation models suggests that training on synthetic tasks can substantially improve in-context learning capabilities, with overall performance largely depending on how well models can infer task-specific predictive relationships from the available context during inference. In this paper, we introduce TAFFY, a tabular foundation model with an In-Context Diversity Prior and a Task-Conditioned Looped Transformer that stren