pinkman123's picture

6 3

pinkman123

pinkmanlove

·

AI & ML interests

GPT!

Recent Activity

upvoted a paper 10 days ago

GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization

upvoted a paper about 2 months ago

ToolOrchestra: Elevating Intelligence via Efficient Model and Tool Orchestration

liked a model 2 months ago

moonshotai/Kimi-K2-Thinking

View all activity

Organizations

None yet

pinkmanlove 's datasets

None public yet