E-GRPO: High Entropy Steps Drive Effective Reinforcement Learning for Flow Models
Paper
•
2601.00423
•
Published
•
8
tuhanbo
tuhanbo
·
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
8 days ago
E-GRPO: High Entropy Steps Drive Effective Reinforcement Learning for Flow Models
upvoted
a
paper
11 days ago
Coupling Experts and Routers in Mixture-of-Experts via an Auxiliary Loss
liked
a model
about 1 month ago
zai-org/GLM-4.5-Air-Base
Organizations
None yet
upvoted
a
paper
8 days ago