Google Research·· 2026-06-30
Introducing TabFM: A zero-shot foundation model for tabular data
Introducing TabFM: A zero-shot foundation model for tabular data
AI summary
Google Research released TabFM for tabular classification and regression. It reframes table prediction as in-context learning, producing predictions in one forward pass without manual training, hyperparameter tuning or feature engineering.
Selection record
Threshold 60Official, first-handFirst 71Second 71
AdmittedSum of both 142 ≥ twice the threshold 120
- Source tier
- Official, first-hand; this tier's threshold is 60
- Pre-filter
- passed：介绍表格数据基础模型TabFM，属AI技术
- Why it was chosen
- Its architecture, synthetic-data training and TabArena results support assessment of whether zero-shot prediction can replace traditional tree-model workflows.
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: Google Research · research.google