Read It Back: Pretrained MLLMs Are Zero-Shot Reward Models for Text-to-Image Generation
Paper • 2607.11886 • Published • 85
Jianhua Han
hanjianhua44
·
AI & ML interests
None yet
Recent Activity
upvoted a paper 28 days ago
Read It Back: Pretrained MLLMs Are Zero-Shot Reward Models for Text-to-Image Generation authored a paper over 1 year ago
ILLUME+: Illuminating Unified MLLM with Dual Visual Tokenization and
Diffusion RefinementOrganizations
