GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization
Paper
•
2601.05242
•
Published
•
202
E
enio
Gargaz's profile picture
Mi6paulino's profile picture
b082f689-ebc3-413d-b1f2-27bd1e86dca7's profile picture
·
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
6 months ago
Qwen3 Technical Report
upvoted
a
paper
6 months ago
MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning
Attention
Organizations
upvoted
a
paper
10 days ago