Thread

TabPFN and TabICL vs. tuned XGBoost: the model that doesn't train won 14/14

23 points · 12 comments · EfrainGaray

rdedev · 1790568428 · focus · HN ↗
Tabular foundation models are one of those things where when you first look into it, it does not make sense as to why they would work so well but it does.
In drug property prediction domain, tabular foundation models coupled with another foundation model for molecules are pretty close to being the state of art.
Btw the article makes heavy use of AI or is written in that way A lot of unnecessary dramatic flair that gets very tiring
1. NordStreamYacht · 1790568679 · focus · HN ↗
  True.
  Why "Every number is a measured one" and not "every parameter is measured?"
  Stopped reading at that point.
  LLMs are like autotune. Imagine the Rolling Stones auto-tuned.

Unofficial Hacker News client; not affiliated with Y Combinator.