Zijun Wang

I am currently a fourth-year undergraduate student at Zhejiang University (ZJU), and my advisor is Prof. Yang Yang. I am also fortunate to be interning with Prof. Cihang Xie at the University of California, Santa Cruz.

My research interests mainly revolve around AI Safety, Natural Language Processing (NLP), Multi-modal learning and their applications.

Specifically, I'm now working on Adversarial Attacks on LLMs & VLLMs.

I am always open to research discussions and collaborations : ) Additionally, I am actively seeking potential Ph.D. or RA. positions enrolling in Fall 2024.

Email  /  Google Scholar  /  Github  /  CV  /  Twitter

News

- Second Place in both base & large model subtracks of Red Teaming LLM@NeurIPS 2023, Torjan Detection Challenge

Publications

How Many Unicorns Are in This Image? A Safety Evaluation Benchmark for Vision LLMs
Haoqin Tu*, Chenhang Cui*, Zijun Wang*, Yiyang Zhou, Bingchen Zhao, Junlin Han, Wangchunshu Zhou, Huaxiu Yao, Cihang Xie (* represents equal contribution)
Technique Report, 2023

GRAPHGENT: Foundation Model for Graph Pre-training
Yifei Sun, Zijun Wang, Xiao Feng, Chunping Wang, Lei CHEN, Jie Tang, Yang Yang
Technique Report, 2023

Experience

Aug. 2023 - Present, VLAA Lab

Visiting Research Intern, Adversarial Attacks on LLMs & VLLMs

Jan. 2023 - Present, Zhejiang University

Research Assistant advised by Prof. Yang Yang, Genaralized Graph Pre-training

Sep. 2020 - Present, Zhejiang University

Undergrad, Current GPA: 3.91/4.0

Awards

- National Scholarship issued by Ministry of Education of the People's Republic of China

- First-class Scholarship of Zhejiang University

- Provincial Government Scholarship of Zhejiang Province

Last Update 11/27/2023. Thanks to Jon Barron.