I am a CS Ph.D. student at Rutgers University, advised by Prof. Ruixiang (Ryan) Tang. Before Rutgers, I completed my master's and bachelor's degrees at the SIGMA Lab of Wuhan University, advised by Prof. Zengmao Wang and Prof. Bo Du.
My research focuses on building trustworthy agentic AI systems, with particular interests in LLM post-training, safety, reliability, and robustness. I also work on reliable detection of AI-generated visual content and interdisciplinary applications of ML in healthcare, including immunology and cell morphology.
🔥 If you share these research interests or have feedback on my previous work, feel free to drop me an email — I am always delighted to discuss potential collaborations!
Selected work — click through to explore each project.
Boxuan Zhang*, Jianing Zhu*, Zeru Shi, Dongfang Liu, Ruixiang Tang
We reframe agentic failure analysis from post-hoc attribution on completed trajectories to online auditing on unfolding prefixes, where an auditor commits a continue-or-alarm verdict at every step.
Boxuan Zhang, Jianing Zhu, Qifan Wang, Jiang Liu, Ruixiang Tang
We propose Micro-Defects expose Macro-Fakes (MDMF), a local distribution-aware detection framework that amplifies micro-scale statistical irregularities into macro-level distributional discrepancies for AI-generated image detection.
Boxuan Zhang*, Jianing Zhu*, Zengmao Wang, Tongliang Liu, Bo Du, Bo Han
Propose a novel perspective to employ different common corruptions on the input space to expand the representation dimension for out-of-distribution detection.
