Small Language Models (SLMs) don’t have the capacity to remember everything in their training data. Which tokens should they learn to predict, and when should they ask for help? We tackle this question in our new preprint. You can check it out on arxiv: arxiv.org/abs/2602.12005 🧵1/7

Show Post

Huge thank you to my co-authors at Apple MLR! @marcocuturi.bsky.social @pierreablin.bsky.social @louisbethune.bsky.social, @danbusbridge, Michal Klein & Jason Ramapuram

Show Post

I am at #NeurIPS2025. We can chat about data mixing, efficient training, ML@Apple and more.

Show Post

Afternoon talks by: @marcocuturi.bsky.social Elena Agliari Jan Gerken Thanks all for the great talks, conversations, and engagement! Fingers crossed we get to host this event a 4th time next year and see many of you back in Gothenburg 🤞🇸🇪

Show Post

🇪🇬 Gawad v Crouin 🇫🇷 | Silicon Valley Open 2025 | FINAL HIGHLIGHTS #squash youtu.be/XKYYUe25l4k?...

Show Post