zijun

Zijun Wang

I am a PhD student at University of California, Santa Cruz (UCSC), and my advisor is Prof. Cihang Xie. I received my BS from Zhejiang University.

My research interests mainly revolve around AI Safety.

I am always open to research discussions and collaborations : )

News

[Jan. 2025] One paper is accepted by TMLR 2025

[Dec. 2024] One paper is accepted by KDD 2025

[Jul. 2024] One paper is accepted by ECCV 2024

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

	STAR-1: Safer Alignment of Reasoning LLMs with 1K Data Zijun Wang, Haoqin Tu, Yuhan Wang, Juncheng Wu, Jieru Mei, Brian R. Bartoldson, Bhavya Kailkhura, Cihang Xie, Technique Report, 2025 paper / project page / code
	AttnGCG: Enhancing Jailbreaking Attacks on LLMs with Attention Manipulation Zijun Wang, Haoqin Tu, Jieru Mei, Bingchen Zhao, Yisen Wang, Cihang Xie, TMLR, 2025 paper / code
	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) ECCV, 2024 paper / code
	Handling Feature Heterogeneity with Learnable Graph Patches Yifei Sun, Yang Yang, Xiao Feng, Zijun Wang, Haoyang Zhong, Chunping Wang, Lei Chen KDD, 2025 paper / code