cs.LGOct 31, 2026

TabAbax: A Tabular Foundation Model Technical Report

Authors: Zhixiong Cheng, Xiaoyun Gao, Shiyuan Han, Jingjing Suo, Zhengli Wang

Organizations: Bairong Inc.AI, Beijing, China

Abstract

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.

Figures & tables

Appendix figures & tables6 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. TabICLv2: A better, faster, scalable, and open tabular foundation model

    Feb 11, 2026Jingang Qu, David Holzmüller, Gaël Varoquaux +1Synthetic Data PretrainingTabular Foundation Models

  2. EXAONE Tabular 1.0 : Technical Report

    Aug 26, 2026Moonjung Eo, Min-Kook Suh, Hye-Seung Cho +4Tabular Foundation ModelsTabular ICL

  3. FTFM: Factorized Tabular Foundation Models

    Oct 18, 2026Josif GrabockaTabular Foundation ModelsTabular ICL