Hi there. I'm Shuai Zhong (鍾帥, /dʒʊŋ1 ʃuaɪ4/), you can also call me Chris. I'm a M.Phil. student @ HKU MMLab, The University of Hong Kong. My research focuses on developing autonomous agents that can perceive, reason, and act in complex multimodal environments - particularly in GUI control and collaborative multi-agent scenarios. 🤖
My work spans from adversarial robustness in VLMs (exploring novel jailbreaking paradigms) to emergent behaviors in multi-agent reinforcement learning systems. Currently, I'm exploring the intersection of Vision-Language Foundation Models and Agentic AI Systems under the supervision of Dr. Ping Luo and co-supervision of Dr. Lingpeng Kong @ HKU-CDS. I also had the privilege of working with Dr. Xihui Liu as my UG FYP advisor @ HKU-EEE.
Warning
Problem: The current name of your GitHub Pages repository ("Solution: Please consider renaming the repository to "
http://".
However, if the current repository name is intended, you can ignore this message by removing "{% include widgets/debug_repo_name.html %}" in index.html.
Action required
Problem: The current root path of this site is "baseurl ("_config.yml.
Solution: Please set the
baseurl in _config.yml to "Education
-
The University of Hong KongM.Phil. in Computer ScienceSep. 2025 - Jul. 2027 (expected) -
The University of Hong KongB.Eng. in Computer EngineeringSep. 2020 - Jul. 2025
Experience
-
TCL Corporate Research (HK) Co., Ltd.Research InternMay 2025 - Present -
HKU MMLabResearch AssistantMay 2025 - Present
-
HKU NLP LabResearch AssistantSep. 2023 - Jan. 2025
-
Hangzhou Raycloud Technology Co., Ltd.Research InternJul. 2022 - Aug. 2022
News
Selected Publications (view all )
SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control
Quanfeng Lu*, Zhantao Ma*, Shuai Zhong, Jin Wang, Dahai Yu, Michael K. Ng, Ping Luo (* equal contribution)
arXiv preprint 2025
SWIRL: A multi-agent RL framework with interleaved updates. Key contributions: (1) Theoretical guarantees & convergence proofs, (2) O(1) memory efficiency, (3) SOTA zero-shot GUI control with only 3.5K examples. Transferable across domains (GUI + math reasoning).
SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control
Quanfeng Lu*, Zhantao Ma*, Shuai Zhong, Jin Wang, Dahai Yu, Michael K. Ng, Ping Luo (* equal contribution)
arXiv preprint 2025
SWIRL: A multi-agent RL framework with interleaved updates. Key contributions: (1) Theoretical guarantees & convergence proofs, (2) O(1) memory efficiency, (3) SOTA zero-shot GUI control with only 3.5K examples. Transferable across domains (GUI + math reasoning).
ImgTrojan: Jailbreaking Vision-Language Models with ONE Image
Xijia Tao*, Shuai Zhong*, Lei Li*, Qi Liu, Lingpeng Kong (* equal contribution)
North American Chapter of the Association for Computational Linguistics (NAACL) 2025 Oral
ImgTrojan: VLM jailbreaking with ONE poisoned image. Key contributions: (1) Training-time attack via malicious image captions, (2) Comprehensive VLM safety evaluation metrics, (3) Systematic vulnerability analysis. Successfully bypasses safety mechanisms across multiple VLM architectures.
ImgTrojan: Jailbreaking Vision-Language Models with ONE Image
Xijia Tao*, Shuai Zhong*, Lei Li*, Qi Liu, Lingpeng Kong (* equal contribution)
North American Chapter of the Association for Computational Linguistics (NAACL) 2025 Oral
ImgTrojan: VLM jailbreaking with ONE poisoned image. Key contributions: (1) Training-time attack via malicious image captions, (2) Comprehensive VLM safety evaluation metrics, (3) Systematic vulnerability analysis. Successfully bypasses safety mechanisms across multiple VLM architectures.