It Takes Two: Your GRPO Is Secretly DPO
Paper
•
2510.00977
•
Published
•
29
Yuchen Hui
Meranti
AI & ML interests
Interests
Recent Activity
upvoted
a
paper
15 days ago
It Takes Two: Your GRPO Is Secretly DPO
new activity
10 months ago
naver/splade-v3:Max coc token length
new activity
11 months ago
Meranti/CLAP_freesound:File size of Freesound(No overlap)?
Organizations
None yet
upvoted
a
paper
15 days ago