Come see my #HSP2026 poster at MIT Building 46 starting in mere moments! I'll be showing you how reading and decision-making are sensitive to the probabilities of the semantic categories of words in joint work with @lgrobol.eu and Ryan Hubbard!

si t'as des infos ou des contacts ça m'intéresse, je suis prof à Nanterre et je découvre seulement ça

on présente notre projet ce soir! viendez!

don't mind this I'm just trying to see something

Hello everyone at #AMLaP25 and also have you found a plug

(hi, aforementioned collaborator here, I've been Proded)

oooh so the maze plugin is functional and i just need to wrap it up nicely before sending a PR but i'd love to see the improvements on spr to see if i can steal ideas from there!

the girl (me) putting tuba (bayesian gaussian mixture models) on girl (you)'s face meme

basically

cass and morgan avatars in gather.town. cass' is wearing a face mask and morgan' a sousaphone

we're truly so cute

currently in the virtual #CMCL2025 poster session with @virmalised.us and a sousaphone

i don't like it but it's true

also @pranav-nlp.bsky.social made me

also incidentally my first paper under my actual name. I'll probably keep using both, but it seemed appropriate for this one

fr

it just feels different idk

I'm really really happy about this one

Helping on this one was really cool, BGMMs are so good!

This is a great thread that you should definitely read. I wrote a little something on diversity-washing this spring.

In French, about how fake Breton-French machine translation systems are actually harmful

mostly for plausible deniability ngl

hej i don't anticipate posting a lot here but uuuh this account exists i guess

-- email template to be sent to legal@wikimedia.org and copy to ca@wikimedia.org (trust&safety) --

Subject: Transphobic rules on French speaking wikipedia

To the attention of the Legal Department of the Wikimedia Foundation,