I am Zian Su, a fourth-year Ph.D. student in Purdue University, Department of Computer Science, advised by Samuel Conte Professor Xiangyu Zhang.

Previously, I obtained my Bachelor degree in Computer Science from Nanjing University (NJU) in 2021. I am grateful to have Prof. Shujian Huang and Prof. Lin Chen as my intial advisors, who introduced me to the world of research. I also had the privilege to work with Dr. Jinman Zhao during my undergrad study.

Research

I am generally interested in code intelligence and language agents. Currently, I am passionate about

• Security Alignment of Code LLMs. To enhance the safety and security of code LLMs via domain knowledge and reinforcement learning.
• Repository-level Code Understanding and Generation. To enhance repository-level code understanding and generation by means of context augmentation (e.g., retrieval) and multi-step LLM reasoning.
• Neural Architecture Design for Code Models. To design neural architectures that effectively and efficiently processes various modalities of code (sequence, graph, etc.) to perform understanding and reasoning.
• Knowledge Editing for LLMs. To develop approaches that effectively modify certain LLM behaviors without heavy re-training.