TabFM (Tabular Foundation Model) is a pretrained tabular foundation… — AI & Deep Learning

AI & Deep Learning@deeplearning005 · 11K subscribers Open in TelegramOpen

TabFM (Tabular Foundation Model) is a pretrained tabular foundation model developed by Google Research for tabular data regression and classification.

At inference time, TabFM does not require training parameters on your dataset; instead, it leverages in-context learning by reading your training data as "context" to make instant predictions on new test samples.

https://github.com/google-research/tabfm