I am Ziyi Zhang (张子怡), a first-year Ph.D. student at the School of Cyber Science and Engineering, Wuhan University, advised by Prof. Xinlei He.

My research interests include trustworthy AI, multimodal large language models, and embodied intelligence.

Before joining Wuhan University, I completed my postgraduate studies at City University of Hong Kong. I received dual bachelor’s degrees in Management and Finance from Jilin University.

I welcome academic discussions and the exchange of research ideas. Please feel free to contact me at ziyizhang26@whu.edu.cn.

🔥 News

• 2025.11: Our paper FC-Attack was published in Findings of EMNLP 2025.
• 2025.07: Our paper on quantifying and monitoring AI-generated text on social media was published in ACL 2025.
• 2025.05: We released preprints on real-time VideoLLMs for visual assistance and fine-grained AI-edited image detection (FragFake).
• 2025.04: We released Humanizing LLMs, a survey of psychological measurements, tools, datasets, and human-agent applications.

📝 Publications & Preprints

Conference Papers

FC-Attack: Jailbreaking Multimodal Large Language Models via Auto-Generated Flowcharts

Ziyi Zhang, Zhen Sun, Zongmin Zhang, Jihui Guo, Xinlei He.

Findings of EMNLP 2025 · pp. 9299–9316

Are We in the AI-Generated Text World Already? Quantifying and Monitoring AIGT on Social Media

Zhen Sun, Zongmin Zhang, Xinyue Shen, Ziyi Zhang, Yule Liu, Michael Backes, Yang Zhang, Xinlei He.

ACL 2025 · Main Conference, Long Papers · pp. 22975–23005

Preprints

“I Can See Forever!”: Evaluating Real-time VideoLLMs for Assisting Individuals with Visual Impairments

Ziyi Zhang, Zhen Sun, Zongmin Zhang, Zifan Peng, Yuemeng Zhao, Zichun Wang, Zeren Luo, Ruiting Zuo, Xinlei He.

arXiv preprint · arXiv:2505.04488 · 2025

Can VLMs Detect and Localize Fine-Grained AI-Edited Images?

Zhen Sun, Ziyi Zhang, Zeren Luo, Zhiyuan Zhong, Zeyang Sha, Tianshuo Cong, Zheng Li, Shiwen Cui, Weiqiang Wang, Jiaheng Wei, Xinlei He, Qi Li, Qian Wang.

arXiv preprint · arXiv:2505.15644 · 2025

Earlier version: FragFake: A Dataset for Fine-Grained Detection of Edited Images with Vision Language Models.

Humanizing LLMs: A Survey of Psychological Measurements with Tools, Datasets, and Human-Agent Applications

Wenhan Dong, Yuemeng Zhao, Zhen Sun, Yule Liu, Zifan Peng, Jingyi Zheng, Zongmin Zhang, Ziyi Zhang, Jun Wu, Ruiming Wang, Shengmin Xu, Xinyi Huang, Xinlei He.

arXiv preprint · arXiv:2505.00049 · 2025

🎖 Honors and Awards

🎓 Education

• Wuhan University
  Ph.D. student, School of Cyber Science and Engineering.
  Advisor: Prof. Xinlei He.

• City University of Hong Kong
  Completed postgraduate studies.

• Jilin University
  Dual bachelor’s degrees in Management and Finance.

💻 Internships

Research Assistant
The Hong Kong University of Science and Technology (Guangzhou)
2024–2026

Conducted research on large language model jailbreaking and multimodal large language models.

📬 Contact

I welcome academic discussions and opportunities to exchange research ideas.

• Email: ziyizhang26@whu.edu.cn
• Affiliation: School of Cyber Science and Engineering, Wuhan University
• Location: Wuhan, Hubei, China
• Google Scholar: Ziyi Zhang
• GitHub: LZhangzy