Model Releases

Google Research launches TabFM: a zero-shot foundation model for tabular data

Original title:Introducing TabFM: A zero-shot foundation model for tabular data

AI summary

Google Research released TabFM, a zero-shot foundation model based on in-context learning (ICL) designed for classification and regression tasks on tabular data. TabFM takes an entire dataset (including training samples and rows to be predicted) as a unified prompt and learns row-column relationships directly from context at inference time, without model training, hyperparameter tuning or feature engineering. Unlike traditional methods that require extensive manual tuning (such as XGBoost), TabFM generates high-quality predictions on new tables through a single forward pass. The model is open-sourced on Hugging Face and GitHub.

Key Takeaways

  • Google Research released TabFM,a zero-shot foundation model based on in-context learning (ICL)…
  • TabFM takes an entire dataset (including training samples and rows to be predicted) as a unified…
  • Unlike traditional methods that require extensive manual tuning (such as XGBoost),TabFM generates…
  • The model is open-sourced on Hugging Face and GitHub.

Quick Facts

Published
Updated
Source
Google Research:Blog(网页)
Category
Model Releases
AI score
76
Read the original Read the full article at the original source
Why it matters

TabFM 把表格预测变成一次前向传播,不再需调参和特征工程,数据科学家可以少熬夜了。BigQuery 集成让使用门槛降到 SQL,这是表格 ML 的零样本时刻。

Related entities

Source & copyright

This article is based on curated titles and AI summaries from the AIHOT public API, with attribution and links back. Original copyright remains with the original publishers and authors; this site does not mirror full texts.

Original article · AIHOT entry

How to Cite

When citing this article, keep the title, date, and permalink, and credit Orange News as the source.

Orange News: Google Research launches TabFM: a zero-shot foundation model for tabular data. June 30, 2026. https://new.nat6.net/en/news/cmr5bqxtn00z1slc77gvm7ybl/

View all →