Adaptation Interfaces for In-Context Tabular Foundation Models in Time-to-Event Prediction
Results indicate that effective TabFM transfer depends on the data regime and on the statistical structure represented by the chosen adaptation interface, and that classification fine-tuning becomes more competitive with zero-shot inference as data sets grow but remains weaker for probabilistic prediction.
Minh-Khoi Pham, Luca Cotugno, Dan Cernei et al.
· 0 citations