it is my great honour to be appointed as the Glen se Vries Professor of Health Statistics. i have quickly written about this in my blog post: kyunghyuncho.me/glen-de-vries-…

!!! I'm at #ICLR2025 to present 🧄Aioli🧄 a unified framework for data mixing on Thursday afternoon! 🔗 arxiv.org/abs/2411.05735 Message me to chat about pre/post training data (mixing, curriculum, understanding); test-time compute/verification; or to try new food 🇸🇬

hot multi agent researcher summer

RL can certainly teach LLMs new skills in principle, but in practice token-level exploration is so challenging that we end up relying on pretraining and synthetic data. the era of experience implies the era of exploration

I'll be at #ACL2025 next week! 🇦🇹 Things on my mind: curriculum learning, online adaptation, LM agents Where to find me: 1⃣ Monday: my team's poster on PeopleJoin (interning at Microsoft) 2⃣ Wednesday: discussing pre-pretraining in Panel 1 Excited to chat! DMs are open 😊

Every time I watch models train, I wish I could tune LR on the fly. It's like cooking: we adjust the dial when the food smells off. We built Interactive Training to do that, turning loss monitoring into interaction. Paper👉huggingface.co/papers/2510.02… Led by Wentao Zhang w/ Yang Lu

i'm getting really tired of "it's not x, it's y" and "do x, not y" in peoples' writing (more accurately, in their ghostwriter's writing). when i see it i honestly just move on and try to delete what i saw from my memory it's not just sloppy, it's also tasteless

📝 New paper! Two strategies have emerged for controlling LLM behavior at inference time: in-context learning (ICL; i.e. prompting) and activation steering. We propose that both can be understood as altering model beliefs, formally in the sense of Bayesian belief updating. 1/9

Everything I know about data mixing, I've learned from Mayee. The best mixer out there👩‍🍳 Very excited that her insights are now part of Olmo's open recipe

It's rare to find formidable theory chops, engineering skill, and a taste for important problems in the same researcher, but that's Will! apply apply apply