Youbin Wu — accepted AI-conference papers

2026

Generative Universal Verifier as Multimodal Meta-Reasoner

Xinchen Zhang, Xiaoying Zhang, Youbin Wu, Yanbin Cao, Renrui Zhang, Ruihang Chu +3

ICLR 2026oral

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…

Cited by 0 Source ↗code ↗Scholar ↗

2026

Revisiting the Necessity of Lengthy Chain-of-Thought in Vision-centric Reasoning Generalization

Yifan Du, Kun Zhou, Yingqian Min, Yue Ling, Wayne Xin Zhao, Youbin Wu +1

CVPR 2026

We study how different Chain-of-Thought (CoT) designs affect the acquisition of the generalizable visual reasoning ability in vision-language models (VLMs). While CoT data, especially long or visual CoT such as "think with image", has been widely used to supervise intermediate reasoning, it remains

Cited by 0 Source ↗code ↗Scholar ↗