Gaël Varoquaux

gaelvaroquaux.bsky.social

29 June 2026 20:54

🧑‍💻🧑‍🏫 I'm recruiting a post-doc to work on Tabular Foundation Models, one of the hotest topics in AI, where we are at the leading edge team.inria.fr/soda/files/2... This is an opportunity to develop the next-level tabular AI, blending deep learning and tables.

Sam Power

spmontecarlo.bsky.social

24 May 2026 09:15

I didn't become a mathematician to have to see numbers like 20/3! (sources math.stackexchange.com/questions/82..., x.com/SSRS_cp/stat...).

Arik Reuter

arikreuter.bsky.social

11 May 2026 07:41

Last year, several “Causal Foundation Models” have been proposed—large, synthetically pre-trained transformers that estimate causal effects via in-context learning. [1-4] However, none of them can flexibly change its predictions based on the most critical assumption in causality: the causal graph.

Ross Floate

rossfloate.bsky.social

10 May 2026 11:49

Oh my. This is spectacular. sinceyouarrived.world/taken

Antoine Moulin

antoine-mln.bsky.social

06 April 2026 08:47

eg, I’m always confused by the regret in advers. settings with bandit feedback. the goal is to teach a blind player to shoot a moving target, and the only reason we can say anything is bc we compare ourselves to a omniscient but paralyzed player who can only shoot in one loc. why does it make sense?