https://www.inceptionlabs.ai/blog/introducing-mercury-2

On Data Engineering for Scaling LLM Terminal Capabilities https://arxiv.org/abs/2602.21193 https://www.alphaxiv.org/ru/overview/2602.21193…

LLMs Can Learn to Reason Via Off-Policy RL https://arxiv.org/abs/2602.19362 https://www.alphaxiv.org/ru/overview/2602.19362

The Art of Efficient Reasoning: Data, Reward, and Optimization https://arxiv.org/abs/2602.20945 https://www.alphaxiv.org/ru/overview/2602.20945

Building a web search engine from scratch in two months with 3 billion neural embeddings https://blog.wilsonl.in/search-engine/

а пока хз использую из торча их мюон, нифига