# Read It Back: Pretrained MLLMs Are Zero-Shot Reward Models for Text-to-Image Generation

Page: https://stenobird.com/podcast/daily-paper-cast-7079649/read-it-back-pretrained-mllms-are-zero-shot-reward-models-for-text-to-image-generation
Text version: https://stenobird.com/podcast/daily-paper-cast-7079649/read-it-back-pretrained-mllms-are-zero-shot-reward-models-for-text-to-image-generation.md
Podcast: [Daily Paper Cast](https://stenobird.com/podcast/daily-paper-cast-7079649)
Published: 2026-07-16T03:36:18+00:00
Episode link: https://share.transistor.fm/s/e28356b6
Audio file: https://media.transistor.fm/e28356b6/007cc336.mp3
Processing state: not_requested
JSON: 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
Duration seconds: 1157

## Resource

🤗 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…

## Actions

- request_transcript: `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.
- read_markdown: `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.

A page view does not enqueue transcription. Agents should invoke `request_transcript` explicitly when they need this episode processed.

## Transcript

Full transcripts are not published on public pages unless there is a clear rights basis.