🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

📢 Excited to share our new paper: Challenges and Paths Towards AI for SWE We discuss: 🛠️ 6 sub-tasks needed for SWE 🤖 9 challenges of today's AI in SWE 🔮 9 future directions to address the challenges w/ collaborators from MIT, Berkeley, Cornell, Stanford, and UPenn ⬇️ (1/n)

We are excited to announce the release of Goedel-Pset (huggingface.co/datasets/Goede…), the largest Lean statement dataset, which contains 1.73 million samples. Goedel-Pset is 10 times larger than Lean Workbook. We hope this resource will facilitate further research within the

Fascinating talk by Thomas Hubert on AlphaProof at IMO 2024! Combining Lean's formal verification with DeepMind's RL techniques led to solving one of the hardest problems that stumped most humans. Watch: youtube.com/watch?v=TFBzP7… #LeanLang #AlphaProof

I am looking to hire a student researcher to work with AlphaProof on a project at the intersection of AI, math, computation, and creativity. Background in AI for math, and/or Lean is desired. If interested, please get in touch. The position will be based in London.

We believe formal math is the future. 🔥Introducing Kimina-Prover Preview, a Numina & Kimi.ai collaboration, the first large formal reasoning model for Lean 4, achieving 80.78% miniF2F. github.com/MoonshotAI/Kim…

What if AI could generate mathematical proofs that can be verified rigorously by machines? 🤖🧮 In Lecture 9 of Advanced LLM Agents MOOC, Kaiyu Yang (Meta FAIR) explores how large language models merge with formal systems like Lean to deliver fully verifiable math! #FormalMath

🔥 Really excited to announce close to 1,000 teams already registered for #AgentX—building the future of Agentic AI across Entrepreneurship & Research tracks! 🚀 💰 Prize pool now $125K+, with total prizes/resources surpassing $400K! 🏆 Highlights: 💸 $40K CASH AWARDS sponsored

I was honored to give a talk on AI for theorem proving for the Berkeley Advanced LLM Agents course! "Bridging Informal and Formal Mathematical Reasoning with AI" Youtube: youtube.com/live/Gy5Nm17l9… Slides: wellecks.com/data/welleck20… It covers three themes from our recent work: -

Come join our AI for Math & Theorem Proving social at #ICLR2025! Looking forward to talking with everyone interested in LLMs for reasoning!

📣 Today 4/21 at 10:10 AM PT, join us for the 11th Advanced LLM Agents MOOC lecture on Program Verification & Generating Verified Code by Swarat Chaudhuri UT Austin. 🌐 Join the thriving community of the LLM Agents MOOC series, with 23K+ registered learners & 10K+ members on

Writing math proof in Lean is surprisingly addictive. Watching Terence Tao formalize Lean proofs feels like watching a top-tier gamer playing on Twitch. :-) youtube.com/watch?v=c1ixXM…

🌟 Excited to announce our esteemed panel of judges for the #AgentX competition by UC Berkeley RDI UC Berkeley. Huge thanks to Xinyun Chen Chi Wang Google DeepMind; Kaiyu Yang Meta; Jay Rodge Zhiding Yu NVIDIA; Somil Aggarwal Schmidt Sciences; Samuel Barry Mistral AI;

DeepSeekProverV2 solves 47/657 problems on PutnamBench! The model represents a substantial advance in theorem proving. The previous best model only solved 10 problems! I'm excited to see DeepSeek's performance on IMO 2025 :)

What’s next for AI and math trib.al/9cahZIc

Do LLMs truly understand math proofs, or just guess? 🤔Our new study on #IneqMath dives deep into Olympiad-level inequality proofs & reveals a critical gap: LLMs are often good at finding answers, but struggle with rigorous, sound proofs. ➡️ ineqmath.github.io To tackle

A mathematical paper autoformalized for the first time: amazing work by Morph, presented today at the Big Proof conference by Jared Duker Lichtman and Jesse Michael Han. I am very impressed by the blazing fast progress of the morph team. Especially by Leyan Pan and _.

1/ 🔥 AI agents are reaching a breakthrough moment in cybersecurity. In our latest work: 🔓 CyberGym: AI agents discovered 15 zero-days in major open-source projects 💰 BountyBench: AI agents solved real-world bug bounty tasks worth tens of thousands of dollars 🤖