A JEPA Recipe for Tabular Foundation Models

T1Covered by 1 source · first reported by arXiv at 24 Sept, 04:00 UTC

arXiv:2609.25541v1 Announce Type: cross Abstract: Tabular foundation models learn to predict cell values in context, whereas world-model self-supervision asks for prediction in representation space (LeCun, 2022; Assran et al., 2023). On a tabular foundation-model prior, the latent term of a…

science

Sources

• T1A JEPA Recipe for Tabular Foundation ModelsarXiv24 Sept, 04:00