Metraipolis › archive › dc_d5db85f17232

TabAbax: A Tabular Foundation Model Technical Report — arXiv:2611.00562

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.00562
License (as archived)
CC0-1.0
Archived
2026-11-03T11:19:27.529Z
SHA-256 of the archived text
96c4f9f9315ce12384d48d657f7133974397675c1434605cd37206f2b8625e2e
Stable URL of this page
https://metraipolis.com/documento/dc_d5db85f17232

How to cite

TabAbax: A Tabular Foundation Model Technical Report — arXiv:2611.00562 — arXiv (en), https://arxiv.org/abs/2611.00562 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d5db85f17232 (Metraipolis archive dc_d5db85f17232, sha256 96c4f9f9315ce12384d48d657f7133974397675c1434605cd37206f2b8625e2e)
BibTeX
@misc{dcd5db85f17232,
  title = {TabAbax: A Tabular Foundation Model Technical Report — arXiv:2611.00562},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.00562},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d5db85f17232; sha256 96c4f9f9315ce12384d48d657f7133974397675c1434605cd37206f2b8625e2e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.00562. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Tabular foundation models (TFMs) enable in-context prediction on unseen tabular datasets without task-specific training. Mechanistic work has shown that increasing the depth of the ICL Transformer yields weak gains, leaving the main headroom for gains in the synthetic pretraining prior and column-row encoder upstream of the ICL backbone. We introduce TabAbax, a TFM built on TabICLv2 that focuses all modifications on these two upstream components. On the prior side, we further improve the quality and complexity of the synthetic pretraining prior. On the encoder side, a two-pass column-row stack strengthens cross-feature interactions before row compression, using learned Fourier scalar encoding from TabFM and Causilo. Evaluations on BeyondArena and TabArena show strong regression-centric gains: TabAbax reaches 1,238 Elo on the 142-dataset BeyondArena suite (10th of 41 evaluated methods), 1,676 Elo on TabArena's overall 51-dataset suite (11th of 99 methods, +115 over TabICLv2), and 2,024 Elo on TabArena's regression benchmark (7th of 99 methods, +336 over TabICLv2, +21 over TabFM). A prior-only ablation confirms the attribution: the improved prior alone yields +228 Elo for regression, demonstrating that prior quality is the dominant knob for improving regression performance.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2611.00562 — 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 2026-11-03T11:02:37.452Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).