TileBench Accepted at AACL 2026
Our paper TileBench: A Controlled Benchmark for Performance Evaluation and Bottleneck Diagnosis of Tile-Based Programming Models, by Bowen Cui, Zhongchun Zhou, Hao Wu, Tejas Ramesh, Junyu Yin, Jialiang Gu, and Keren Zhou, has been accepted at AACL-IJCNLP 2026. TileBench compares tile-based GPU programming models under controlled conditions and supports profiling-guided diagnosis of performance bottlenecks. Congratulations to all the authors!
Bowen Cui
2024 Fall –
Bowen Cui is a second-year Ph.D. student at George Mason University advised by Prof. Keren Zhou. His research interests focus on LLM-based code agents, benchmarking, and performance optimization.
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.
Tejas Ramesh
2023 Fall -
My research interests include Artificial Intelligence and High Performance Computing
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.
