Alexander Du

profile_picture.jpg

I am a third-year Ph.D. student in Computer Science at Duke University, advised by Prof. Matthew Lentz and Prof. Danyang Zhuo. I received my B.S. in Computer Science and Mathematics from Duke in 2024.

My research interests broadly span machine learning systems. I currently focus on fine-grained GPU resource management. My previous work sits at the intersection of programming languages and machine learning, including code generation, proof synthesis, and verification of ML systems.

Outside of research, I play piano and violin, go rock climbing, and practice calligraphy.

Publications

2026

  1. Preprint
    Trellis: Bringing Compiler-Guided Repair into Agentic Code Generation
    Alexander Du, Jianjun Ou, Danyang Zhuo, and Matthew Lentz
    arXiv preprint arXiv:2605.15238, 2026

2025

  1. HotOS
    Can Large Language Models Verify System Software? A Case Study Using FSCQ as a Benchmark
    Jianxing Qin, Alexander Du, Danfeng Zhang, Matthew Lentz, and Danyang Zhuo
    In Workshop on Hot Topics in Operating Systems (HotOS), 2025

2024

  1. IEEE VRW
    Did You Do Well? Real-Time Personalized Feedback on Catheter Placement in Augmented Reality-Assisted Neurosurgical Training
    Sangjun Eom, Tiffany Ma, Neha Vutakuri, Alexander Du, Zhehan Qu, Joshua Jackson, and Maria Gorlatova
    In IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops (VRW), 2024