cs.LGNov 17, 2026

NVIDIA Kumo Tabular: Pushing the Accuracy\unicode8211\unicode{8211}Efficiency Frontier for Tabular Prediction

Authors: Jingang Qu, Valter Hudovernik, Martin Jurkovič, Cedric Lorenz, David Holzmüller, Federico Lopez, Dmitry Gordeev, Akihiro Nitta, 

Organizations: NVIDIA · INRIA · Stanford University

Abstract

We introduce Kumo Tabular, a family of open tabular foundation models for classification and regression, in three sizes: Kumo Tabular-S (27M parameters), Kumo Tabular-M (61M), and Kumo Tabular-L (214M). Pretrained only on artificial tables from the Kumo prior, they can make predictions on new tables without any training. In our approach, a table encoder compresses each row into an embedding, and an in-context learning transformer predicts the unlabeled rows from the labeled ones. Kumo Tabular introduces architectural innovations that improve both training stability and predictive performance, enabling the model to scale up to 150M cells on modern GPUs. Kumo Tabular-L ranks first on eight benchmarks: TabArena, TALENT, BeyondArena, ScoringBench, STRABLE, MulTaBench, RamanBench, and TabBench-Bio. These cover probabilistic regression, tables with over 1M rows or 100K columns, and tables with strings, text, or images. Accuracy improves with model size in all tested comparisons. All three sizes lie on the accuracy-speed frontiers of TabArena and BeyondArena. Kumo Tabular-L predicts faster than the runners-up, LimiX-2 on TabArena (36 times) and TabPFN-3.5 on BeyondArena (1.7 times). Weights and pretraining code are released under OpenMDW-1.1 and Apache 2.0, respectively.

Figures & tables

Appendix figures & tables6 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. TabPFN-3.5: Technical Report

    Sep 15, 2026Benjamin Jäger, Nick Erickson, Léo Grinsztajn +44Tabular Foundation ModelsInference-Time Optimization

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

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

  3. EXAONE Tabular 1.0 : Technical Report

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