Jul 2026
Read It Back: Pretrained MLLMs Are Zero-Shot Reward Models for Text-to-Image Generation
SpectraReward is proposed, a training-free reward function that turns pretrained MLLMs into off-the-shelf reward models for image-generation reinforcement learning, and Self-SpectraReward is introduced, a special case for unified multimodal models where the policy's own understanding branch serves as the reward model for its generation branch.
Runhu Huang, Qihui Zhang, Zhe Liu et al.
· arXiv.org · 0 citations