E-GRPO: High Entropy Steps Drive Effective Reinforcement Learning for Flow Models
Paper
•
2601.00423
•
Published
•
8
adrian
adriandj3
AI & ML interests
ai
Recent Activity
upvoted
a
paper
3 days ago
E-GRPO: High Entropy Steps Drive Effective Reinforcement Learning for Flow Models
upvoted
a
paper
6 days ago
IMA++: ISIC Archive Multi-Annotator Dermoscopic Skin Lesion Segmentation Dataset
upvoted
a
paper
10 days ago
On the Role of Discreteness in Diffusion LLMs
Organizations
None yet