| title | OmniVerifier-M1: Multimodal Meta-Verifier with Explicit Structured Recalibration |
|---|---|
| authors | Xinchen Zhang, Bowei Liu, Jiale Liu, Chufan Shi, Yizhen Zhang, Junhong Liu, Youliang Zhang, Zhiheng Li, Yujiu Yang, Ling Yang |
| date | 2026-05-27 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2605.28805 |
| upvotes | 8 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf |
| abstract | Visual outcomes are increasingly central to multimodal large language models, making reliable and fine-grained verification essential for scaling generalist foundation models. In this work, we investigate multimodal meta-verification, which leverages verifier-generated rationales rather than decision-only signals, and explore how to effectively incorporate meta-verification feedback into multimodal verifier training. We identify two key findings. First, symbolic verifier outputs (e.g., bounding boxes) outperform textual explanations as meta-verification rationales, enabling efficient rule-based reinforcement learning rewards while avoiding reliance on model-based rewards from auxiliary judge models. Second, decoupling reinforcement learning objectives for binary judgment and meta-verification substantially outperforms joint reward optimization, due to intrinsic differences in output structure and learning dynamics. Based on these insights, we train OmniVerifier-M1, a generalist visual verifier leveraging symbolic meta-verification and decoupled reinforcement learning. OmniVerifier-M1 provides robust verification and fine-grained error localization, and further enables M1-TTS, a verifier-driven agentic generation system achieving dynamic region-level self-correction. This approach paves the way for more reliable, interpretable, and fine-grained multimodal verification, supporting safer and more controllable foundation model deployment. |
cite
@misc{zhang2026omniverifier,
title={OmniVerifier-M1: Multimodal Meta-Verifier with Explicit Structured Recalibration},
author={Xinchen Zhang and Bowei Liu and Jiale Liu and Chufan Shi and Yizhen Zhang and Junhong Liu and Youliang Zhang and Zhiheng Li and Yujiu Yang and Ling Yang},
year={2026},
eprint={2605.28805},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2605.28805}
}