Metraipolis › archive › dc_7b8da920c50e

A JEPA Recipe for Tabular Foundation Models — arXiv:2609.25541

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.25541
License (as archived)
CC0-1.0
Archived
2026-10-08T13:46:27.521Z
SHA-256 of the archived text
bde3b0896176427543c06f458deaac09c3363152752cf283d9fb9c4c9d7b7afc
Stable URL of this page
https://metraipolis.com/documento/dc_7b8da920c50e

How to cite

A JEPA Recipe for Tabular Foundation Models — arXiv:2609.25541 — arXiv (en), https://arxiv.org/abs/2609.25541 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7b8da920c50e (Metraipolis archive dc_7b8da920c50e, sha256 bde3b0896176427543c06f458deaac09c3363152752cf283d9fb9c4c9d7b7afc)
BibTeX
@misc{dc7b8da920c50e,
  title = {A JEPA Recipe for Tabular Foundation Models — arXiv:2609.25541},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.25541},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7b8da920c50e; sha256 bde3b0896176427543c06f458deaac09c3363152752cf283d9fb9c4c9d7b7afc},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.25541. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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 joint-embedding predictive architecture (JEPA) collapsed in our earlier runs and took the encoder with it to a constant map. We report a recipe under which the latent term survives to convergence beside the value objective: the value head reads the encoder field rather than the predictor, and the target is an exponential moving average (EMA) difference. To bound its cost against the value-only arm, both arms train until a plateau rule stops them, with no fixed step budget. A fixed horizon had confounded a slowdown with a ceiling, since the value-only arm was still improving well past the usual budget. At convergence, in one run per arm, the JEPA arm trails the value-only arm across 147 real datasets, 32:70 wins to losses on classification (29:63 with one entry per dataset name) and 8:24 on regression, the margin small on classification and wider on regression, and the count leans the same way in each stratum and each benchmark. The JEPA arm (jepa) needs 1.42 times as many steps as the value-only arm (ds), and 1.66 times its wall-clock, to reach its plateau.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-23 in cs.AI).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.25541 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-08T13:18:38.238Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-23?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).