NKI Teaching Lab Accepted at SIGCSE TS 2027
Our paper NKI Teaching Lab: An Accelerator-Free Toolchain for Learning Tile-Level AI Accelerator Programming, by Jialiang Gu, Junjie Ma, Thai-Hoa Nguyen, Hao Wu, Zhicong Lu, Shuyin Jiao, Binqian Yin, and Keren Zhou, has been accepted at SIGCSE TS 2027, the ACM Technical Symposium on Computer Science Education. The teaching lab helps students learn tile-level AI accelerator programming without accelerator hardware. Congratulations to all the authors!
Jialiang Gu
2025 Fall -
CS PhD student at George Mason University advised by Prof. Keren Zhou. I work at the intersection of ML systems & AI compilers (Triton/NKI), LLM agents for algorithmic code repair and debugging (TLE), tile-semantics analysis & tooling, and discourse-aware summarization.
Hao Wu
2024 Spring -
My research interests lies in tools for Machine Learning Workloads, including profilers for ML, compilers for ML and program analysis tool for AI compiler.
