NVIDIA Kumo Tabular Sets a New Accuracy-Efficiency Frontier for Tabular Prediction
NVIDIA Kumo Tabular Sets a New Accuracy-Efficiency Frontier for Tabular Prediction
NVIDIA released Kumo Tabular, an open-source tabular foundation model that predicts labels for new rows in a single forward pass given labelled rows, without training, tuning or feature engineering. It supports classification and regression, offers three sizes from 28M to 215M, and was pretrained solely on artificially generated tables. It uses the commercially usable OpenMDW-1.1 licence and ranks first on TabArena, BeyondArena, TALENT and ScoringBench.
Selection record
AdmittedSum of both 143 ≥ twice the threshold 120
- Source tier
- Official, first-hand; this tier's threshold is 60
- Pre-filter
- passed：NVIDIA发布表格预测基础模型，属AI模型技术
- Why it was chosen
- Details the tabular foundation model’s architecture, training data sources and rankings on four benchmarks, helping assess the limits of training-free tabular prediction.
A model scores each item twice, independently, against one written standard, out of 100. An item is admitted only when the two scores add up to twice the threshold. The threshold is set per source tier.
Source: Hugging Face Blog · huggingface.co