OptimalScale

AI & ML interests

Large foundation models, large language models.

Recent Activity

research4pan  authored a paper 14 days ago

GAR: Generative Adversarial Reinforcement Learning for Formal Theorem Proving

hendrydong  authored a paper 5 months ago

Fractured Chain-of-Thought Reasoning

hendrydong  authored a paper 6 months ago

Beyond 'Aha!': Toward Systematic Meta-Abilities Alignment in Large Reasoning Models

View all activity

Team members 6