--- format: "aidr-story-markdown/v1" id: "4776c9d6004936e9732ea63a71c99134ff73f3451a855bb340f252f755fd9a79" canonical_url: "https://aidr.today/4776c9d6?lang=en" title: "NVIDIA Releases Kumo Tabular: Open Tabular Foundation Models That Predict New Rows in a Single Forward Pass" lang: "en" requested_lang: "en" available_langs: ["en","vi"] translation_fallback: null fallback_fields: [] published_at: "2026-10-01T06:57:50.000Z" category: "Releases" topics: ["nvidia","open-source"] source_urls: ["https://www.marktechpost.com/2026/09/30/nvidia-releases-kumo-tabular/"] summary: "NVIDIA has released Kumo Tabular, a new family of tabular foundation models (TFMs) for classification and regression. If you have followed TabPFN or TabICL, the setup will look familiar. The model takes labeled rows as context and predicts new rows in one forward pass. There is no training, no hyperparameter tuning, and no feature engineering. […] The post NVIDIA Releases Kumo Tabular: Open Tabular Foundation Models That Predict New Rows in a Single Forward Pass appeared first on MarkTechPost ." --- # NVIDIA Releases Kumo Tabular: Open Tabular Foundation Models That Predict New Rows in a Single Forward Pass > [Open the canonical story]() **Published:** 2026-10-01T06:57:50.000Z **Category:** Releases **Topics:** nvidia, open\-source ## Summary NVIDIA has released Kumo Tabular, a new family of tabular foundation models \(TFMs\) for classification and regression\. If you have followed TabPFN or TabICL, the setup will look familiar\. The model takes labeled rows as context and predicts new rows in one forward pass\. There is no training, no hyperparameter tuning, and no feature engineering\. \[…\] The post NVIDIA Releases Kumo Tabular: Open Tabular Foundation Models That Predict New Rows in a Single Forward Pass appeared first on MarkTechPost \. ## Sources - [Story source]()