It Takes Two: Your GRPO Is Secretly DPO
Paper
•
2510.00977
•
Published
•
27
Liheng Ma
lihengma
AI & ML interests
Graph Machine Learning; Geometric Deep Learning
Recent Activity
authored
a paper
5 days ago
It Takes Two: Your GRPO Is Secretly DPO
upvoted
a
paper
5 days ago
It Takes Two: Your GRPO Is Secretly DPO
updated
a model
5 months ago
lihengma/Qwen-2.5-7B-Instruct_2wiki_text_mrl_v7
Organizations
upvoted
a
paper
5 days ago