my handwritten poster on emnlp2023. Look like many are interested

🚀 Excited to introduce TheoremLlama! 🎉 Our new framework transforms general-purpose LLMs into Lean4 experts. Achieving 36.48% and 33.61% on MiniF2F-Valid and Test, surpassing the GPT-4 baseline of 22.95% and 25.41%. 🌟 Check out our open-sourced Open Boostrapped Theorems

🚀 Introducing Goedel-Prover: A 7B LLM achieving SOTA open-source performance in automated theorem proving! 🔥 ✅ Improving +7% over previous open source SOTA on miniF2F 🏆 Ranking 1st on the PutnamBench Leaderboard 🤖 Solving 1.9X total problems compared to prior works on Lean

I'm hiring full-time research scientists and interns for my new team, the Verifiable AI Lab at MiroMindAI (SF Bay Area). As AI systems take on harder and longer-horizon tasks, a fundamental bottleneck emerges: human review doesn't scale, and models that can't check their own