---
title: "Tabular Data"
description: "1 posts about Tabular Data, summarised, each linking to the original."
---

# Tabular Data
> 1 posts about Tabular Data, summarised, each linking to the original.

## Articles

### [NVIDIA Kumo Tabular Sets a New Accuracy-Efficiency Frontier for Tabular Prediction](https://yomu.fyi/post/nvidia-kumo-tabular-sets-a-new-accuracy-efficiency-frontier-for-tabula.md)
- Company: [Hugging Face](https://yomu.fyi/company/hugging-face.md)
- Author: Jingang Qu, Valter Hudovernik, Martin Jurkovic, Cedric Lorenz, Akihiro Nitta, Dmitry Gordeev, Federico Lopez, Ramona Bendias, Gilberto Titericz Jr, Aleksandar S. Sokolovski, Isabel Hulseman, Jure Leskovec, Matthias Fey
- Published: Sep 29, 2026
- Type: Announcement

NVIDIA Kumo Tabular is an open foundation model for tabular classification and regression that predicts labels in a single forward pass without training, tuning, or feature engineering. It uses a Transformer architecture with column, row, and in-context attention, including length-aware attention temperature to maintain sharp attention on large tables. Pretrained entirely on artificial tables generated from structural causal models with realistic imperfections such as missing values, coarsened features, and heavy-tailed targets, it comes in three sizes (28M to 215M parameters) and handles missing values without imputation. On the TabArena, BeyondArena, TALENT, and ScoringBench benchmarks, Kumo Tabular achieves top rankings and establishes a new accuracy-efficiency frontier, running 17x faster than LimiX-2. The model is available on Hugging Face under the OpenMDW-1.1 license and runs via NVIDIA’s open-source structured-data-models library.