Project Numina

🎉 An open problem in control theory solved by Pr. Amaury Hayat with the Project Numina AI prover! In boundary stabilization of nonlinear hyperbolic PDEs, the L^2 criteria is always the least restrictive. 👉 See full thread and proof here https://lnkd.in/dhTZHsAT https://lnkd.in/dw2JSEXB Cc Jia Li Thibaut Barroyer Stanislas Polu François Charton XTX Markets Alexandre Momeni

We are launching the Numina Fellowship 🚀

We have unlocked a new paradigm in automated reasoning 🙂 🚀 We are deeply grateful for the foundational contributions of the entire Mathlib community. We hope you will enjoy using Numina-Lean-Agent as much as we enjoyed building it!

Congratulations to our contributors Mantas Bakšys and Jonas Bayer for being invited to give a talk during the AITP 2025 conference! 💪🚀 They deep dived into the capabilities of our Kimina prover, which uses a Chain of (Formal) Thought reasoning pattern, allowing it to generate complex, human-like proofs and achieve an 92.2% pass rate on the miniF2F benchmark. 👀 We believe in open scientific collaboration. By open-sourcing our models and datasets, we aim to accelerate progress and build tools that bridge the gap between human intuition and formal verification. 👉 links in the comments #AI4Math #FormalMath #LeanProver #AutomatedReasoning #TheoremProving #ProofAssistant #MachineLearning #AIResearch #OpenScience #Lean4 #LeanLang

We are proud to be Releasing NuminaMath-LEAN, a large-scale dataset of 100K mathematical competition problems formalized in Lean 4, with more than 20K human annotations. 🔥💪 Paired with Kimina-Prover, Kimina-autoformalizer, CombiBench, we hope these data and models will advance open-source AI for formal mathematics ! This year's IMO was bittersweet for Numina as our theorem prover did not solve any problem, we believed we were very close. 👉 Numina is starting a new chapter after IMO 2025. While we will still continue to build SOTA open source theorem prover for high school problems, we would also like to branch out and explore undergraduate level math or even research level, open mathematical problems. #AI4Math #FormalMath #LeanProver #AutomatedReasoning #TheoremProving #ProofAssistant #MachineLearning #AIResearch #OpenScience #Lean4 #LeanLang

New milestone for Project Numina and Kimi Moonshot! 🚀 We are open sourcing our KiminaProver-72B. This SotA theorem-proving model comes with Test-Time Reinforcement Learning Search and Error-Fixing Capability. We’re putting it to the test soon, with the IMO just around the corner 👀 Check it out 👉 https://lnkd.in/guHfgtwZ Read the blog post https://lnkd.in/gGrSkuPJ #AI4Math #FormalMath #LeanProver #AutomatedReasoning #TheoremProving #ProofAssistant #MachineLearning #AIResearch #OpenScience #Lean4 #LeanLang