Generative Universal Verifier as Multimodal Meta-Reasoner

ICLROral2026

Authors
Xinchen Zhang, Xiaoying Zhang, Youbin Wu, Yanbin Cao, Renrui Zhang, Ruihang Chu, Ling Yang, Yujiu Yang, Guang Shi
Affiliation
ByteDance Seed
Venue
ICLR 2026
Track
Oral

TL;DR

We introduce *Generative Universal Verifier*, a novel concept and plugin designed for next-generation multimodal reasoning in vision-language models and unified multimodal models, providing the fundamental capability of reflection and refinement on visual outcomes during the reasoning and generation process. This work makes three main contributi...

Opening excerpt from the authors’ abstract. source

Read the paper

Topics

vision-language language model multimodal reasoning

← All ICLR 2026 Oral papers · Browse the whole archive