Read It Back: Pretrained MLLMs Are Zero-Shot Reward Models for Text-to-Image Generation
In this paper, we propose SpectraReward, a training-free reward function that turns pretrained MLLMs into off-the-shelf reward models for image-generation reinforcement learning. Instead of asking the MLLM to judge a generated image or answer decomposed verification questions, SpectraReward measures how well the original prompt can be recovered from the generated image through a single image-conditioned, teacher-forced forward pass. We use the average image-conditioned prompt log-likelihood as the reward, directly reusing the MLLM's pretrained image-text alignment ability without preference la
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- LinkedLinked via arxiv author · 85%Runhui Huang →
“Read It Back: Pretrained MLLMs Are Zero-Shot Reward Models for Text-to-Image Generation”
- LinkedLinked via arxiv author · 85%Qihui Zhang →
“Read It Back: Pretrained MLLMs Are Zero-Shot Reward Models for Text-to-Image Generation”
- LinkedLinked via arxiv author · 85%Yuanzhe Liu →
“Read It Back: Pretrained MLLMs Are Zero-Shot Reward Models for Text-to-Image Generation”
- LinkedLinked via arxiv author · 85%Yu Gao →
“Read It Back: Pretrained MLLMs Are Zero-Shot Reward Models for Text-to-Image Generation”
- LinkedLinked via arxiv author · 85%Dai-Jie Wu →
“Read It Back: Pretrained MLLMs Are Zero-Shot Reward Models for Text-to-Image Generation”
- LinkedLinked via arxiv author · 85%Hengshuang Zhao →
“Read It Back: Pretrained MLLMs Are Zero-Shot Reward Models for Text-to-Image Generation”