Google's TabFM: Zero-Shot Tabular Foundation Model

Google Research unveils TabFM, a foundation model for tabular data that performs zero-shot classification and regression without per-dataset training or hyperparameter tuning.

One continuously updated timeline instead of dozens of separate articles. New developments are appended as the story evolves.

1. AnnouncementJun 30, 2026, 10:26 AM 85%

   Google Research introduces TabFM, a zero-shot foundation model for tabular data tasks, reducing the need for labeled datasets.

   Google Research introduces TabFM, a zero-shot foundation model designed to handle tabular data tasks without task-specific training.

   Read the full story →
2. 21 hours later
   ReleaseJul 1, 2026, 07:48 AM 77%

   Google Research releases TabFM, a hybrid-attention foundation model for zero-shot tabular classification and regression.

   Google Research unveils TabFM, a foundation model for tabular data that performs zero-shot classification and regression without per-dataset training or hyperparameter tuning.

   Read the full story →