GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization
Paper
•
2601.05242
•
Published
•
225
Halil Ibrahim Hatun
halilibr
AI & ML interests
Generative AI, Computer Vision, Data Science, etc...
Recent Activity
upvoted
a
paper
about 1 month ago
GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization
liked
a model
5 months ago
RedHatAI/Qwen2.5-VL-72B-Instruct-FP8-dynamic
liked
a dataset
5 months ago
ysdede/khanacademy-turkish
Organizations
None yet
upvoted
a
paper
about 1 month ago