Read It Back: Pretrained MLLMs Are Zero-Shot Reward Models for Text-to-Image Generation
Paper • 2607.11886 • Published • 84
Ding
Scipio1996
AI & ML interests
None yet
Recent Activity
upvoted a paper 7 months ago
Reinventing Clinical Dialogue: Agentic Paradigms for LLM Enabled Healthcare Communication upvoted a paper almost 2 years ago
VideoHallucer: Evaluating Intrinsic and Extrinsic Hallucinations in
Large Video-Language ModelsOrganizations
None yet