Tag: theorem-proving
All the articles with the tag "theorem-proving".
-
DeepSeekMath-V2: Towards Self-Verifiable Mathematical Reasoning
DeepSeekMath-V2 scored 118/120 on Putnam 2024—surpassing the human record of 90—and achieved IMO gold level. The key innovation: a self-verification architecture where models learn to identify and fix their own proof errors.