Profile avatar
bennokrojer.bsky.social
AI PhDing at Mila/McGill (prev FAIR intern). Happily residing in Montreal 🥯❄️ Academic: language grounding, vision+language, interp, rigorous & creative evals, cogsci Other: many sports, urban explorations, puzzles/quizzes bennokrojer.com
1,710 posts 2,564 followers 937 following
Regular Contributor
Active Commenter
Posts 13 Comments 37

I would only use if it there were direct verbatim quotes from sources mentioned as the primary answer. Otherwise same, scroll past it

submitted 12 hours ago • 0 comments

Super useful! I didn't actually know this trick

submitted 1 day ago • 1 comment

I will miss Thomas Müller One of the greats of football

submitted 1 day ago • 0 comments

This week, Mila researchers will present more than 90 papers at @iclr-conf.bsky.social in Singapore. Every day, we will share a schedule featuring Mila-affiliated presentations. Day 1 👇 #ICLR2025 mila.quebec/en/news/foll...

submitted 4 days ago • 0 comments

Fulfilling the male cliche and learning about the fall of the Roman empire which is definitely not related to any current events

submitted 5 days ago • 0 comments

Now the paper is also on arxiv and can be easily cited: arxiv.org/abs/2504.07128

submitted 16 days ago • 1 comment

My friend @sshkhr.bsky.social created this cool tool to track all kinds of ML summer schools - check it out!

submitted 18 days ago • 0 comments

Has anyone had a situation where an arxiv submission is on hold for more than a week? What are usually causes for this?

submitted 19 days ago • 1 comment

My labmates made a cool thing The video is also fun to watch!

submitted 23 days ago • 0 comments

Really enjoyed diving deep into this paper today: arxiv.org/abs/2406.16860 It's so systematic and a treasure trove full of insights

submitted 23 days ago • 0 comments

Here is a great summary of the paper: www.youtube.com/watch?v=aO_c... @sivareddyg.bsky.social gave a talk today at the Simon's institute workshop on The Future of Language Models and Transformers

submitted 25 days ago • 1 comment

Never been part of a project like this before - it was a very rewarding+unique experience! Everyone in the lab contributed different chapters and it was much more exploratory than your average phd project. My chapter studied R1's reasoning on "image generation/editing" (via ASCII) 🧵👇 1/N

submitted 26 days ago • 1 comment

Which evals do you pay attention the most when judging how good a new VLM is?

submitted 26 days ago • 0 comments