NVIDIA has introduced Kumo Tabular, a family of tabular foundation models built for classification and regression tasks. The company said the models use labeled rows as context and can predict a new row in a single forward pass, without training, hyperparameter tuning, or feature engineering. The lineup includes small, medium, and large versions, with parameter counts ranging from about 28 million to 215 million.
Kumo Tabular runs through NVIDIA’s open-source Structured Data Models, or SDM, library, and its weights are released under the OpenMDW-1.1 license, which allows commercial use. NVIDIA said the models were fully pre-trained on synthetic tables sampled from structural causal models, while also incorporating real-world data patterns such as missing values and high-cardinality categories.
According to the NVIDIA team, Kumo Tabular ranked first on the TabArena benchmark with an Elo score of 1950 under default settings. The team also reported that it runs 17 times faster than LimiX-2 on a single RTX 6000 Pro. The item was cited by MarkTechPost in the Techub News report.
NVIDIA has released Kumo Tabular, a family of tabular foundation models designed for classification and regression tasks, according to a Techub News report.
The company said Kumo Tabular uses labeled rows as context and can predict a new row in a single forward pass, without training, hyperparameter tuning, or feature engineering. The series comes in small, medium, and large versions, with parameter counts ranging from about 28 million to 215 million. It runs through NVIDIA’s open-source Structured Data Models (SDM) library, and the weights are distributed under the OpenMDW-1.1 license, which permits commercial use.
For pre-training, the model family was trained entirely on synthetic tables sampled from structural causal models (SCM). NVIDIA also said the training setup introduced real-world data patterns including missing values and high-cardinality categories.
The NVIDIA team reported that, under default settings, Kumo Tabular ranked No. 1 on the TabArena benchmark with a 1950 Elo score. It also said the model runs 17 times faster than LimiX-2 on a single RTX 6000 Pro. The report cited MarkTechPost.
This article was originally published by Bit.Fan. For more cryptocurrency news and market insights, visit www.bit.fan. Disclaimer:
The market information, project data, and third-party content displayed on this platform are for industry information sharing only and do not constitute any form of investment advice or return commitment.
Cryptocurrency trading carries high risks. Users should fully assess their risk tolerance and make independent decisions. All profits, losses, and legal responsibilities are borne by the users themselves.
