-
Pref-GRPO: Pairwise Preference Reward-based GRPO for Stable Text-to-Image Reinforcement Learning
Paper • 2508.20751 • Published • 87 -
CodeGoat24/UniGenBench-Eval-Images
Viewer • Updated • 2.4k • 897 • 2 -
CodeGoat24/UniGenBench
Updated • 163 • 1 -
CodeGoat24/FLUX.1-dev-PrefGRPO
Text-to-Image • Updated • 47 • 3
SII-Yibin Wang
CodeGoat24
AI & ML interests
I'm part of Shanghai Innovation Institute, focusing on Multimodal RL and Generation.
Recent Activity
updated
a dataset
about 2 hours ago
CodeGoat24/UniGenBench-Eval-Images
updated
a Space
about 2 hours ago
CodeGoat24/UniGenBench_Leaderboard_English_Long
updated
a Space
about 2 hours ago
CodeGoat24/UniGenBench_Leaderboard_Chinese_Long