For those interested, you may find my tutorial slides (that keep updating) at kzhang66.github.io/slides_Kaiqing…

Check out Soheil Feizi’s new RELAI agents! Looks super cool

Max has been a fantastic collaborator and colleague, inspired me to think a lot more about bridging practice and relevant theory. More importantly, his enthusiasm and strong work ethic made him an amazing mentor for young students! I am sure it will be a blast working with him!

A bit of good news 😉 Happy New Year everyone!

We propose Unified Fine-Tuning (UFT) — a novel post-training framework that unifies Supervised Fine-Tuning (SFT) and Reinforcement Fine-Tuning (RFT), and outperforms both. 📈 Superior performance across model sizes and tasks. 📚 Theory-backed: Achieves exponential improvement in

Russ's recent talk at Stanford has to be my favorite in the past couple of years. I have asked everyone in my lab to watch it. youtube.com/watch?v=TN1M6v… IMO our community has accrued a huge amount of "research debt" (analogous to "technical debt") through flashy demos and

TRI's latest Large Behavior Model (LBM) paper landed on arxiv last night! Check out our project website: toyotaresearchinstitute.github.io/lbm1/ One of our main goals for this paper was to put out a very careful and thorough study on the topic to help people understand the state of the

Super fun work on post-"co"-training multiple LLM agents using RL! Check Chanwoo Park 's thread below 🔽. Just accepted as ACL Main Conference lately, check it out if u are interested!

Thanks Chi Jin ! Looking forward as well :)!