AI TrackerFrontier desk · AEST
Back to news
normalaitech

NVIDIA Kumo Tabular Sets a New Accuracy-Efficiency Frontier for Tabular Prediction

Hugging Face · 30 Sept 2026, 01:30 AEST

NVIDIA has introduced Kumo Tabular, a new foundation model designed for tabular classification and regression. This model leverages in-context learning to predict labels from tables efficiently.

Key facts

Read aloud

NVIDIA has introduced Kumo Tabular, a new foundation model designed for tabular classification and regression. This model leverages in-context learning to predict labels from tables efficiently. Tabular data is the backbone of enterprise machine learning. For two decades, this work has been done with gradient-boosted trees, and it has worked well. Kumo Tabular is a Transformer built around the structure of a table, utilizing column, row and in-context attention. Given a table with labeled rows and the rows you want predictions for, Kumo Tabular returns class probabilities or numeric predictions in a single forward pass.

Sources in this cluster