Google's TabFM: a zero-shot foundation model that predicts table data in one forward pass
Prompt Engineering · youtube · 2026-10-11
Google Research released TabFM, a zero-shot foundation model for tabular data: feed it the rows you know and it predicts the rest in a single forward pass with no training. The video explains how it learns from synthetic tables, why it can't read column names, and how TabFM-Auto wraps an LLM agent around it. The author builds that agent on Neon Postgres for churn prediction, showing how a leaky column fooled the agent and how a database history branch fixed it. Paper, code, and weights are all public.
More from coding & agent
- Anatomy: a Claude Code skill that turns any idea into an interactive machine drawing — _AustinCalvert_ · 2026-10-11
- Fine-tuned SD1.5 generates 16×16 Minecraft item sprites you can drop into resource packs — yuuki202800 · 2026-10-11
- 16x Microsoft MVP demos Jev, a PowerShell AI workflow for ranking and routing requests — dfinke · 2026-10-11
- rec-rs: a clean-room Rust rewrite of OBS for macOS using only Apple frameworks — Rasmic · 2026-10-11
- Provenance gateway turns AI agent tool calls into audit-grade, tamper-evident records — hutsonlabs · 2026-10-11
- Evals are replays: store tasks in R2, sandbox in Docker, and 90% of the work is measuring — danshipper · 2026-10-11