| title | Read It Back: Pretrained MLLMs Are Zero-Shot Reward Models for Text-to-Image Generation |
|---|---|
| authors | Runhui Huang, Qihui Zhang, Zhe Liu, Yu Gao, Jie Wu, Hengshuang Zhao |
| date | 2026-07-13 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2607.11886 |
| affiliation | ByteDance Seed |
| upvotes | 57 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf |
| abstract | 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 labels, reward-model fine-tuning. We further introduce Self-SpectraReward, a special case for unified multimodal models where the policy's own understanding branch serves as the reward model for its generation branch, forming a closed-loop self-improving framework without external reward models or external knowledge. Extensive experiments validate SpectraReward through a broad image-generation RL study covering two diffusion models, three RL algorithms, nine reward MLLM backbones from four MLLM families spanning 4B to 235B parameters, and five out-of-distribution text-to-image benchmarks. Results show that both SpectraReward and Self-SpectraReward significantly and consistently improve generation performance and outperform prior MLLM-derived reward training methods. Further analysis reveals that larger reward MLLMs are not always better, while Self-SpectraReward can match or surpass much larger external reward models, suggesting that reward-policy alignment is a key factor for effective image-generation RL. Project Page: https://huangrh99.github.io/SpectraReward/ |
cite
@misc{huang2026read,
title={Read It Back: Pretrained MLLMs Are Zero-Shot Reward Models for Text-to-Image Generation},
author={Runhui Huang and Qihui Zhang and Zhe Liu and Yu Gao and Jie Wu and Hengshuang Zhao},
year={2026},
eprint={2607.11886},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2607.11886}
}