Publications: Tilus: A Tile-Level GPGPU Programming Language for Low-Precision Computation (to appear in ASPLOS 2026); Hidet: Task-Mapping Programming Paradigm for Deep Learning Tensor Programs (published in ASPLOS 2023). Awards: 2023 Qualcomm Innovation Fellowship.
Research Experience
Currently a fourth-year Ph.D. student at the University of Toronto, conducting research under the supervision of Professor Gennady Pekhimenko.
Education
Ph.D. student at the Department of Computer Science, University of Toronto, supervised by Professor Gennady Pekhimenko; Master's degree from the University of Toronto; Bachelor's degree from Shanghai Jiao Tong University (ACM Honors Class), majoring in Computer Science.
Background
Research interests lie in the general area of systems for machine learning, focusing on the design of domain-specific programming languages for tensor programming on modern GPUs and the implementation of the corresponding compilers. Also interested in low-precision computation for large language models.
Miscellany
Personal projects: Open-sourced Tilus project, available at https://github.com/NVIDIA/tilus.