E-GRPO: High Entropy Steps Drive Effective Reinforcement Learning for Flow Models
Paper • 2601.00423 • Published • 11
tuhanbo
tuhanbo
·
AI & ML interests
None yet
Recent Activity
liked a Space 24 days ago
open-llm-leaderboard/open_llm_leaderboard upvoted a paper 7 months ago
E-GRPO: High Entropy Steps Drive Effective Reinforcement Learning for Flow Models upvoted a paper 7 months ago
Coupling Experts and Routers in Mixture-of-Experts via an Auxiliary LossOrganizations
upvoted 2
papers 7 months ago