Pref-GRPO: Pairwise Preference Reward-based GRPO for Stable Text-to-Image Reinforcement Learning
Paper • 2508.20751 • Published • 91
cat
blackdemonimmortal
AI & ML interests
None yet
Recent Activity
liked a Space about 1 month ago
ziheng1234/ImageCritic liked a model 5 months ago
fal/flux-klein-9b-virtual-tryon-lora new activity 5 months ago
fal/flux-klein-9b-virtual-tryon-lora:Question about training data source and scaleOrganizations
None yet
upvoted a paper 12 months ago