SyncAI.news, a Varaisys broadcasting
NVIDIA Kumo Tabular: Pushing the Accuracy$\unicode{8211}$Efficiency Frontier for Tabular Prediction
JQ

Jingang Qu, Valter Hudovernik, Martin Jurkovi\v{c}, Cedric Lorenz, David Holzm\"uller, Federico Lopez, Dmitry Gordeev, Akihiro Nitta, Ramona Bendias, Ardrian Wong, Vedaant Jain, Vignesh Kothapalli, Gilberto Titericz Junior, Jure Leskovec, Matthias Fey

· 1 min read

ResearcharXiv cs.LG

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

arXiv:2611.23001v1 Announce Type: new 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.

Original source

This story was published by arXiv cs.LG and written by Jingang Qu, Valter Hudovernik, Martin Jurkovi\v{c}, Cedric Lorenz, David Holzm\"uller, Federico Lopez, Dmitry Gordeev, Akihiro Nitta, Ramona Bendias, Ardrian Wong, Vedaant Jain, Vignesh Kothapalli, Gilberto Titericz Junior, Jure Leskovec, Matthias Fey. SyncAI.news shows a preview; the complete article is on the publisher's site.

Read the full story on arxiv.org

Similar News