ABOUT ME
I am Zhen Xu, a Master’s student in Computer Science at the University of North Carolina at Chapel Hill, advised by Professor Tianlong Chen. I received my B.Eng in Computer Science and Technology from Zhejiang University, and spent Summer 2024 at Peking University working on network measurement research.
My work currently focuses on large language models and Mixture of Experts (MoE), including model architecture design, optimization, and understanding the interpretability and explainability of these systems. I am also interested in AI for biological applications, where I use AI methods to tackle biological problems such as predicting biological rhythms and patterns.
Publications
2026
LLM-Sketch: Enhancing Network Sketches with LLM
Yuanpeng Li, Zongwei Lv, Zhen Xu, Yannan Hu, Yong Cui, Tong Yang
under-review · 2026
Repudiation Prompt Injection Attack to LLM-based Resume Screening
Zhen Xu, Mohan Zhang, Zhen Tan, Neil Zhenqiang Gong, Tianlong Chen
under-review · 2026
LLM-Guided Heterogeneous Hypergraph Modeling for Pharmacological Relation Discovery
Sukwon Yun*, Zhen Xu*, Ren Wang, Jun Wen, Quan Sun, Song Wang, Can Chen, Tianlong Chen
* denotes co-first authors
under-review · 2026
2025
Does AI Reviewer See the Full Picture? Attacking and Defending Multimodal Peer Review
Xinyu Zhao, Rana Shahroz, Zhen Xu, Zhen Tan, Tianlong Chen
under-review · 2025
Beyond Redundancy: Diverse and Specialized Multi-Expert Sparse Autoencoder
Zhen Xu, Zhen Tan, Song Wang, Kaidi Xu, Tianlong Chen
arxiv · 2025