Yongchang Zhang张用长

I am an incoming Ph.D. student (Fall 2027) and a member of the PKU-VaLuE Lab (Vision-Language and Embodied AI), advised by Prof. Yiwu Zhong at Peking University. My current research focuses on embodied AI, in particular vision-language-action (VLA) models and world action models (WAMs).

I am completing my B.Eng. in Software Engineering at Southeast University, where I am fortunate to be advised by Prof. Yang Chen (School of Computer Science and Engineering) and Prof. Guangquan Zhou (School of Biological Science and Medical Engineering). There I worked on medical image analysis and vision-language models, including training-free methods for visually grounded multimodal reasoning.

• 2026Joined the PKU-VaLuE Lab, advised by Prof. Yiwu Zhong.
• 2026.02See It, Say It, Sorted is accepted to CVPR 2026.

1. See It, Say It, Sorted: An Iterative Training-Free Framework for Visually-Grounded Multimodal Reasoning in LVLMs

   Yongchang Zhang*, Oliver Ma*, Tianyi Liu, Guangquan Zhou, Yang Chen

   A plug-and-play decoding method that checks each reasoning step against visual evidence to curb hallucination in LVLMs, with no extra training.

   CVPR 2026arXivCode

   

Full list on Google Scholar

• 2023 – 2027

  Southeast University

  B.Eng. in Software Engineering

  Advisors: Prof. Yang Chen & Prof. Guangquan Zhou