GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization
Paper
•
2601.05242
•
Published
•
198
Vadim Smolyakov
vsmolyakov
AI & ML interests
Machine Learning Engineer @ Microsoft
Recent Activity
liked
a model
2 months ago
moonshotai/Kimi-K2-Thinking
liked
a model
3 months ago
MiniMaxAI/MiniMax-M2
Organizations
None yet
upvoted
a
paper
3 days ago
upvoted
an
article
8 months ago
Article
The Large Language Model Course
•
217
upvoted
an
article
over 1 year ago
Article
SemScore: Evaluating LLMs with Semantic Similarity
•
15
upvoted
a
collection
almost 2 years ago