E-GRPO: High Entropy Steps Drive Effective Reinforcement Learning for Flow Models
Paper
•
2601.00423
•
Published
•
9
Shengjun Zhang
zhangsj0722
·
AI & ML interests
None yet
Recent Activity
authored
a paper
19 days ago
Scene Splatter: Momentum 3D Scene Generation from Single Image with
Video Diffusion Model
authored
a paper
19 days ago
ScenePainter: Semantically Consistent Perpetual 3D Scene Generation with
Concept Relation Alignment
authored
a paper
19 days ago
E-GRPO: High Entropy Steps Drive Effective Reinforcement Learning for Flow Models
Organizations
None yet