Guangzhi (Allen) Su

I’m Guangzhi (Allen) Su, a senior in the Duke–Duke Kunshan dual-degree program majoring in Applied Math and Computer Science. I work with Prof. Kaizhu Huang (Signature Work) from Duke Kunshan University and as a research intern with Profs. Yiran Chen and Neil Zhenqiang Gong from Duke University. My research spans large language models and multimodal LLMs, multi-agent systems, and generative image models, with a focus on AI safety, efficiency, and clinical applications.

Outside of research, I am the founding president of the DKU Computer Science Club and the DKU Finance Club, and serve as a student advisor for the DKU AI Club, leading initiatives including HackDKU 2024, HackDKU 2025. I was endorsed as Chair of the Student Advocacy Committee of the inaugural Student Leaders Board at DKU, where I work to ensure that students’ voices are represented in university policies and campus life. In 2023, I was also selected as a United Nations Millennium Fellow, working on education equity and cross-cultural exchange. I love singing and sports; I spent four years as a tenor in the DKU Chorus and one year on the DKU badminton varsity team.

Research Interests

• AI Safety
  • Adversarial attacks and defenses for deep and multimodal models
  • AI-generated content detection and watermarking
  • Privacy risks and membership inference attacks
• Efficient AI Systems
  • Token and patch pruning for large models
  • Parallel and distributed training/inference
  • Mixture-of-experts (MoE) architectures for scalable deployment
• AI in Clinical and Healthcare Applications
  • Adverse event detection from clinical videos
  • AI-assisted decision making for clinicians
  • Fairness and reliability of models used in healthcare workflows