-
Pref-GRPO: Pairwise Preference Reward-based GRPO for Stable Text-to-Image Reinforcement Learning
Paper • 2508.20751 • Published • 87 -
CodeGoat24/FLUX.1-dev-PrefGRPO
Text-to-Image • Updated • 44 • 3 -
CodeGoat24/UniGenBench
Updated • 131 • 1 -
CodeGoat24/UniGenBench-Eval-Images
Preview • Updated • 280 • 2
SII-Yibin Wang
CodeGoat24
AI & ML interests
I'm part of Shanghai Innovation Institute, focusing on Multimodal RL and Generation.
Recent Activity
updated
a Space
about 1 hour ago
CodeGoat24/UniGenBench_Leaderboard_Chinese_Long
updated
a dataset
about 1 hour ago
CodeGoat24/UniGenBench-Eval-Images
updated
a dataset
about 2 hours ago
CodeGoat24/UniGenBench