It Takes Two: Your GRPO Is Secretly DPO
Paper
• 2510.00977 • Published
• 32 •
5
Yihong Wu
Yihong7788
AI & ML interests
None yet
Recent Activity
commented on
a paper
12 days ago
It Takes Two: Your GRPO Is Secretly DPO upvoted a paper 5 months ago
It Takes Two: Your GRPO Is Secretly DPO upvoted a paper 5 months ago
On Predictability of Reinforcement Learning Dynamics for Large Language
Models Organizations
None yet
commented a paper 12 days ago
commented a paper 5 months ago