Episode
Read It Back: Pretrained MLLMs Are Zero-Shot Reward Models for Text-to-Image Generation
- Podcast
- Daily Paper Cast
- Published
- Jul 16, 2026
- Duration seconds
- 1157
- Processing state
not_requested- Canonical source
- https://share.transistor.fm/s/e28356b6
Actions
POST https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/read-it-back-pretrained-mllms-are-zero-shot-reward-models-for-text-to-image-generation/transcription-requests
Idempotently request low-priority transcript generation for this episode.GET https://stenobird.com/podcast/daily-paper-cast-7079649/read-it-back-pretrained-mllms-are-zero-shot-reward-models-for-text-to-image-generation.md
Read the agent-friendly Markdown representation of this episode resource.
Summary
🤗 Upvotes: 47 | cs.CV Authors: Runhui Huang, Qihui Zhang, Zhe Liu, Yu Gao, Jie Wu, Hengshuang Zhao Title: Read It Back: Pretrained MLLMs Are Zero-Shot Reward Models for Text-to-Image Generation Arxiv: http://arxiv.org/abs/2607.11886v1 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-p…