Skip to content
NewA calmer, faster ZeroHour

TabFM: A Zero-Shot Foundation Model for Tabular Data

Hugging Face daily papersby Weihao Kong, Erez Louidor Ilan, Shuxin Nie ()1 min read1
Part of a story covered by 2 sourcesTabFM and TabFM-Auto Lead Tabular BenchmarksMerged summary & timeline
AI summary · grok-4.7Summaries by Vani AI

TabFM, a 400M tabular foundation model, delivers calibrated zero-shot predictions that beat tuned AutoML.

TabFM is a 400-million-parameter foundation model that treats supervised tabular prediction as in-context learning and outputs calibrated zero-shot predictions in one forward pass. It is trained only on synthetic tables generated from structural causal models. Across all 51 TabArena datasets, 38 classification and 13 regression, zero-shot TabFM ranks first among default tabular foundation models and beats tuned AutoML pipelines. Frozen-weight extensions TabFM+ and TabFM-Auto further improve both tracks.

Key facts
  • 400M-parameter model trained only on synthetic causal tables
  • Zero-shot predictions in one forward pass, with no task tuning
  • Ranks first among default tabular models on all 51 TabArena sets
  • TabFM+ and TabFM-Auto improve results on frozen base weights
Explain this AI news with Vani AIWhat was announced, what is new and why it matters, in a new chat

From the original article

1 min read at huggingface.co

Tabular machine learning typically relies on per-dataset workflows, fitting tree ensembles or running AutoML searches from scratch for every task. We present TabFM, a 400M-parameter tabular foundation model that formulates supervised tabular prediction as in-context learning. TabFM produces calibrated zero-shot predictions in a single forward pass without task-specific tuning.

Hugging Face daily papers

By Weihao Kong, Erez Louidor Ilan, Shuxin Nie · huggingface.co

Read the full article at Hugging Face daily papers

A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.