Bio
I am an assistant professor of School of Artificial Intelligence at Shenzhen University [Homepage]. My research areas cover large model agents, multimodal learning and video understanding, with applications in multimedia content analysis, AI medical, and AI4Science, aiming to solve real-world problems with advanced AI technology.
I obtained my Ph.D. degree in School of Science and Engineering of The Chinese University of Hong Kong, Shenzhen (CUHK-SZ). I was lucky to be advised by Prof. Rui Huang, Dr. Tao Mei and Prof. Chang-Wen Chen. Previously, I worked as a researcher and postdoctoral fellow at Sangfor Technologies and Chinese Academy of Sciences, where I participated in building China's first cybersecurity LLM Sangfor Security GPT and the CoStrict AI coding agent.
I am recruiting master students for 2027, welcome to contact me [See details]. Students who are interested in my research are also welcome to contact me. I am open to research collaboration—feel free to reach out!
我正在招收2027届推免硕士,欢迎联系。同时,也欢迎对我研究方向感兴趣的同学,与我交流合作!
News
- [Always~] I am looking for self-motivated Undergraduate and Graduate students. Feel free to contact me for research guidance or collaboration.
- [2026.08] I have open‑sourced a practical AI agent tutorial, Hands‑On Agent Building: From AI Digital Employees to One‑Person Companies 《动手构建智能体:从 AI 数字员工到一人公司》. GitHub: https://github.com/gitzyong812/agent_tutorial
- [2026.07] One paper Coder-R3: Recognize, Review and Repair Defective Code with Finetuned LLMs in Practice was accepted to CICAI 2026.
- [2026.03] One paper Boosting Knowledge-based Visual Question Answering with Structured Context Reasoning was accepted to ICME 2026.
- [2025.11] One paper Appearance-Motion Decomposed Alignment for Text-Video Retrieval was accepted to AAAI 2026.
- [2026.03] I joined the School of Artificial Intelligence at Shenzhen University as an Assistant Professor.
- [2023.07] I obtained my Ph.D. degree from CUHK-SZ.
Research Interests
- Research areas: Large models and agents, computer vision, vision-language multimodal learning, video understanding, etc.
- Application scenarios: Multimedia content analysis, AI medical, and AI4Science, aiming to solve real-world problems with advanced AI technology.
Education & Experiences
Selected Publications [Google Scholar]
End-to-End Video Scene Graph Generation with Temporal Propagation Transformer
Yong Zhang, Yingwei Pan, Ting Yao, Rui Huang, Tao Mei, and Chang-Wen Chen
In IEEE Transactions on Multimedia (TMM), 2023
Boosting Scene Graph Generation with Visual Relation Saliency
Yong Zhang, Yingwei Pan, Ting Yao, Rui Huang, Tao Mei, and Chang-Wen Chen
In ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM), 2023
Performance analysis of touch-interaction behavior for active smartphone authentication
Chao Shen, Yong Zhang, Xiaohong Guan, and Roy A. Maxion
In IEEE Transactions on Information Forensics and Security (TIFS), 2015
Touch-interaction behavior for continuous user authentication on smartphones
Chao Shen, Yong Zhang, Zhongmin Cai, Tianwen Yu, and Xiaohong Guan.
In International Conference on Biometrics (ICB), 2015






