Check out Jerry Chi's great talk on our Goedel-Prover!!!👏

We are glad that arxiv.org/abs/2411.18872 evaluate our Goedel-Prover (goedel-lm.github.io) on IMO lemmas and compare it with O3-mini as well as Deepseek-Prover-RL. Our model solved 37.9% of the IMO lemmas and O3-mini only solved 23.8%. It is interesting that

Nothing like a sunny hike to welcome spring!

I sent a message to my PhD students and postdocs at Princeton University a couple of weeks ago regarding freezes/cuts to federal research funding (this was before the freeze on federal funding to Princeton). I am sharing it here in case others find it helpful in having similar

Group hike through the pine trees in Wharton State Forest 🌲🍃

Our VP of Reinforcement Learning David Silver believes we must go “beyond what humans know” - moving towards systems that can learn for themselves, and even discover new scientific knowledge. 🧠 Listen in on his conversation with our podcast host @FryRSquared →

Our warmest congratulations to ⁦Danqi Chen⁩, ⁦Stanford NLP Group⁩ grad and now Associate Professor at ⁦Princeton Computer Science⁩ and Associate Director of ⁦Princeton PLI⁩ on her stunning ⁦⁦ICLR 2025⁩ keynote!

[1] Kids improve when a good teacher offers adaptive, targeted feedback. Can a small LLM benefit if a large LLM provide helpful feedback, in-context?? Naive ideas fail here. We propose AdaptMI: adaptive, skill-based in-context supervision that boosts 1B models by 6% on