Dang Kai's picture

Dang Kai

dangkai-nk

·

AI & ML interests

None yet

Recent Activity

upvoted a paper 10 days ago

Stabilizing Reinforcement Learning with LLMs: Formulation and Practices

upvoted a paper 6 months ago

Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning

upvoted a paper 7 months ago

WorldPM: Scaling Human Preference Modeling

View all activity

Organizations

dangkai-nk 's models

None public yet