Zijun Wang

Zijun Wang

I am a PhD student in Computer Science and Engineering at University of California, Santa Cruz (UCSC), advised by Prof. Cihang Xie in the VLAA Lab. I received my Bachelor of Engineering in Computer Science and Technology from Zhejiang University.

My research focuses on autonomous agents, data-centric LLM training, and AI safety and alignment.

I am currently interning at Amazon in Palo Alto, working on RSI agents and research world models with Hanqing Lu.

I am always open to research discussions and collaborations : )

Email / Google Scholar / GitHub / CV / LinkedIn / Twitter

News

[2026] Your Agent, Their Asset and Harness Updating Is Not Harness Benefit are accepted by EMNLP 2026.

[2026] Chasing the Public Score is accepted by COLM 2026.

[2026.06] I joined Amazon in Palo Alto as an intern, working on RSI agents and research world models with Hanqing Lu.

[2026.06] VisualClaw is out! A real-time, personalized agent for the physical world.

[2026.04] NAG and InfoLaw are accepted by ICML 2026

[2026.04] We release VLAA-GUI, the verified best open-source GUI systems on OSWorld!

[2026.04] CIK-Bench is out! A real-world safety analysis exposing architectural vulnerabilities of personal AI agents.

[2026.02] MIRA is accepted by CVPR 2026

[2025.11] STAR-1 is accepted by AAAI 2026 (oral)

[2025.06] I'm joining ByteDance as Research Scientist Intern.

[2025.04] STAR-1 is out! Using just 1K data to make your reasoning LLMs much safer.

[2025.01] AttnGCG is accepted by TMLR 2025

[2024.12] Graph Patches is accepted by KDD 2025

[2024.07] Unicorns is accepted by ECCV 2024

[2023.12] Second Place in both base & large model subtracks of Red Teaming LLM@NeurIPS 2023, Trojan Detection Challenge [Code]

Selected Publications

2026
	Your Agent, Their Asset: A Real-World Safety Analysis of OpenClaw Zijun Wang, Haoqin Tu, Letian Zhang, Hardy Chen, Juncheng Wu, Xiangyan Liu, Zhenlong Yuan, Tianyu Pang, Michael Qizhe Shieh, Fengze Liu, Zeyu Zheng, Huaxiu Yao, Yuyin Zhou, Cihang Xie EMNLP 2026 paper / project page / code / dataset
	Harness Updating Is Not Harness Benefit: Disentangling Evolution Capabilities in Self-Evolving LLM Agents Minhua Lin, Juncheng Wu, Zijun Wang, Zhan Shi, Yisi Sang, Bing He, Zewen Liu, Tianxin Wei, Zongyu Wu, Zhiwei Zhang, Dakuo Wang, Xiang Zhang, Benoit Dumoulin, Cihang Xie, Yuyin Zhou, Suhang Wang, Hanqing Lu (* represents equal contribution) EMNLP 2026 paper / code
	VisualClaw: A Real-Time, Personalized Agent for the Physical World Haoqin Tu, Jianwen Chen, Zijun Wang, Siwei Han, Juncheng Wu, Hardy Chen, Haonian Ji, Kaiwen Xiong, Jiaqi Liu, Peng Xia, Jieru Mei, Hongliang Fei, Jason Eshraghian, Zeyu Zheng, Yuyin Zhou, Huaxiu Yao, Cihang Xie (* represents equal contribution) In submission to NeurIPS 2026 paper / project page / code
	VLAA-GUI: Knowing When to Stop, Recover, and Search, A Modular Framework for GUI Automation Qijun Han, Haoqin Tu, Zijun Wang, Haoyue Dai, Yiyang Zhou, Nancy Lau, Alvaro A. Cardenas, Yuhui Xu, Ran Xu, Caiming Xiong, Zeyu Zheng, Huaxiu Yao, Yuyin Zhou, Cihang Xie (* represents equal contribution) In submission to NeurIPS 2026 paper / project page / code
	Target-Oriented Pretraining Data Selection via Neuron-Activated Graph Zijun Wang, Haoqin Tu, Weidong Zhou, Yiyang Zhou, Xiaohuan Zhou, Bingni Zhang, Weiguo Feng, Taifeng Wang, Cihang Xie, Fengze Liu ICML 2026 paper / project page / code
	STAR-1: Safer Alignment of Reasoning LLMs with 1K Data Zijun Wang, Haoqin Tu, Yuhan Wang, Juncheng Wu, Yanqing Liu, Jieru Mei, Brian R. Bartoldson, Bhavya Kailkhura, Cihang Xie AAAI 2026 (oral) paper / project page / code / dataset / models
	Chasing the Public Score: User Pressure and Evaluation Exploitation in Coding Agent Workflows Hardy Chen, Nancy Lau, Haoqin Tu, Shuo Yan, Xiangyan Liu, Zijun Wang, Juncheng Wu, Michael Qizhe Shieh, Alvaro A. Cardenas, Cihang Xie, Yuyin Zhou COLM 2026 paper / project page / code
	MIRA: When Visualizing is the First Step to Reasoning, a Benchmark for Visual Chain-of-Thought Yiyang Zhou, Haoqin Tu, Zijun Wang, Zeyu Wang, Niklas Muennighoff, Fan Nie, Yejin Choi, James Zou, Chaorui Deng, Shen Yan, Haoqi Fan, Cihang Xie, Huaxiu Yao, Qinghao Ye (* represents equal contribution) CVPR 2026 paper / project page / code / dataset
	InfoLaw: Information Scaling Laws for Large Language Models with Quality-Weighted Mixture Data and Repetition Fengze Liu, Weidong Zhou, Binbin Liu, Ping Guo, Zijun Wang, Bingni Zhang, Yifan Zhang, Yifeng Yu, Xiaohuan Zhou, Taifeng Wang ICML 2026 paper
2025
	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
	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
	AHELM: A Holistic Evaluation of Audio-Language Models Tony Lee, Haoqin Tu, Chi Heem Wong, Zijun Wang, Siwei Yang, Yifan Mai, Yuyin Zhou, Cihang Xie, Percy Liang arXiv 2025 paper / website / leaderboard / code
	Where on Earth? A Vision-Language Benchmark for Probing Model Geolocation Skills Across Scales Zhaofang Qian, Hardy Chen, Zeyu Wang, Li Zhang, Zijun Wang, Xiaoke Huang, Hui Liu, Xianfeng Tang, Zeyu Zheng, Haoqin Tu, Cihang Xie, Yuyin Zhou arXiv 2025 paper / code
	Mimicking the Physicist's Eye: A VLM-centric Approach for Physics Formula Discovery Jiaqi Liu, Songning Lai, Pengze Li, Di Yu, Wenjie Zhou, Yiyang Zhou, Peng Xia, Zijun Wang, Xi Chen, Shixiang Tang, Lei Bai, Wanli Ouyang, Mingyu Ding, Huaxiu Yao, Aoran Wang arXiv 2025 paper / project page / code
2024
	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

Experience

	Aug. 2024 - Present, VLAA Lab, UC Santa Cruz PhD student in Computer Science and Engineering, advised by Prof. Cihang Xie. Expected graduation: Jun. 2028. Aug. 2023 - Aug. 2024, VLAA Lab, UC Santa Cruz Visiting Research Intern advised by Prof. Cihang Xie, Adversarial Attacks on LLMs & VLLMs
	Jun. 2026 - Present, Amazon, Palo Alto, CA Intern advised by Hanqing Lu, working on RSI agents and research world models. Co-authored Harness Updating Is Not Harness Benefit (EMNLP 2026).
	Jun. 2025 - Apr. 2026, ByteDance, San Jose, CA Research Scientist Intern advised by Fengze Liu, working on foundation LLM pretraining. First-authored NAG for target-oriented pretraining data selection and co-authored InfoLaw for data-aware scaling laws; both accepted by ICML 2026.
	Jan. 2023 - Jul. 2023, Zhejiang University Research Assistant advised by Prof. Yang Yang, Generalized Graph Pre-training Sep. 2020 - Jun. 2024, Zhejiang University Bachelor of Engineering in Computer Science and Technology, GPA: 3.92/4.0

Awards

- Second Place in both base and large model subtracks of the NeurIPS 2023 Trojan Detection Challenge, Red Teaming LLM track; team leader. [Code]

- National Scholarship (top 0.2% nationwide), Ministry of Education of the People's Republic of China, 2021

- First-class Scholarship of Zhejiang University

- Provincial Government Scholarship of Zhejiang Province

Last Update 2026.10.05. Thanks to Jon Barron.