SpectralPO

AI & ML interests

None defined yet.

Recent Activity

ziniuli  authored a paper 16 days ago

Why Transformers Need Adam: A Hessian Perspective

ziniuli  authored a paper 16 days ago

ReMax: A Simple, Effective, and Efficient Reinforcement Learning Method for Aligning Large Language Models

ziniuli  authored a paper 16 days ago

CoRT: Code-integrated Reasoning within Thinking

View all activity

Team members 3