🔥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

We are excited to introduce Mercury, the first commercial-grade diffusion large language model (dLLM)! dLLMs push the frontier of intelligence and speed with parallel, coarse-to-fine text generation.

proof that RL is the future

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…

Combinatorics are the two last problems unsolved by AlphaProof at last year's IMO。 Introducing CombiBench Kimi.ai , a benchmark focusing on combinatorics problems ! 🔥 🏆moonshotai.github.io/CombiBench/ 📘Dataset -> huggingface.co/datasets/AI-MO…

We just released DeepSeek-Prover V2. - Solves nearly 90% of miniF2F problems - Significantly improves the SoTA performance on the PutnamBench - Achieves a non-trivial pass rate on AIME 24 & 25 problems in their formal version Github: github.com/deepseek-ai/De…

wow big day for multi-turn GRPO incredible writeup too

Had fun training Kevin! We explored multi-turn training to help models learn longer-horizon dynamics, and kernel generation seemed a very nice environment to try out our ideas—a step closer to coding agents! 🚀 It turns out that maybe you don't need insanely long context...

Congrats, great work! Also happy to see it's trained on QwQ!

Great work! We love how vLLM is used in the rollout process with with offloading the engine to CPU and give the GPU back to the kernel to be benchmarked! This is a small feature we implemented to make RLHF smoother with vLLM.

Some really great work from Carlo Pietro Marsella Ben Pan! Still a long horizon ahead for multi-turn agents :)

first math pope?

We are excited to announce Trinity, an autoformalization system for verified superintelligence that we have developed at Morph. We have used it to automatically formalize in Lean a classical result of de Bruijn that the abc conjecture is true almost always.

Day 1/5 of #MiniMaxWeek: We’re open-sourcing MiniMax-M1, our latest LLM — setting new standards in long-context reasoning. - World’s longest context window: 1M-token input, 80k-token output - State-of-the-art agentic use among open-source models - RL at unmatched efficiency:

Introducing Reinforcement-Learned Teachers (RLTs): Transforming how we teach LLMs to reason with reinforcement learning (RL). Blog: sakana.ai/rlt Paper: arxiv.org/abs/2506.08388 Traditional RL focuses on “learning to solve” challenging problems with expensive LLMs and

Happy to introduce Kimina-Prover-72B ! Reaching 92.2% on miniF2F using Test time RL. It can solve IMO problems using more than 500 lines of Lean 4 code ! Check our blog post here: huggingface.co/blog/AI-MO/kim… And play with our demo ! demo.projectnumina.ai

(1/4)🚨 Introducing Goedel-Prover V2 🚨 🔥🔥🔥 The strongest open-source theorem prover to date. 🥇 #1 on PutnamBench: Solves 64 problems—with far less compute. 🧠 New SOTA on MiniF2F: * 32B model hits 90.4% at Pass@32, beating DeepSeek-Prover-V2-671B’s 82.4%. * 8B > 671B: Our 8B

Our Goedel-Prover-V2 doubled the SOTA Pass@32 performance on PutnamBench with a 20x smaller model, making it the strongest open-source theorem prover to date!

Typically for these AI results, like in Go/Dota/Poker/Diplomacy, researchers spend years making an AI that masters one narrow domain and does little else. But this isn’t an IMO-specific model. It’s a reasoning LLM that incorporates new experimental general-purpose techniques.

Why am I excited about IMO results we just published: - we did very little IMO-specific work, we just keep training general models - all natural language proofs - no evaluation harness We needed a new research breakthrough and Alexander Wei and team delivered

On IMO P6 (without going into too much detail about our setup), the model "knew" it didn't have a correct solution. The model knowing when it didn't know was one of the early signs of life that made us excited about the underlying research direction!