2 papers
cs.LG2026
Topological Signatures of Context-Level Reliability in TabPFN
James Hu, Mahdi Ghelichi
TabPFN is a transformer-based foundation model for tabular prediction that performs inference without task-specific training by conditioning on a support set and query inputs. Desp…
cs.LG2026
Noise Immunity in In-Context Tabular Learning: An Empirical Robustness Analysis of TabPFN's Attention Mechanisms
James Hu, Mahdi Ghelichi
Tabular foundation models (TFMs) such as TabPFN (Tabular Prior-Data Fitted Network) are designed to generalize across heterogeneous tabular datasets through in-context learning (IC…