Tiancheng (Alex) Zhao

Tiancheng (Alex) Zhao Master Student, Computer Science Georgia Institute of Technology Email: alexzhao2000@outlook.com [GoogleScholar]  [LinkedIn]  [CV]

About me

I am an incoming PhD student at Hong Kong University of Science and Technology, focusing on software-hardware co-design and machine learning systems under the supervision of Prof. Chaojian Li. I received my Master's degree in Computer Science from Georgia Tech, where I was advised by Prof. Helen Xu and specialized in computer systems and high-performance computing. Previously, I received my Bachelor's degree with honors from Shandong University, where I was advised by Prof. Weiguo Liu. I also spent a year at Hong Kong University of Science and Technology, where I worked with Prof. Jiasi Shen as a research postgraduate student, focusing on code comprehension and regeneration. I have also been fortunate to work with Dr. Xin He at A*STAR Singapore.
They have set an example for me as a researcher —— always doing interesting things, pursuing own interests and sticking to them.

Research Interests

• Software-Hardware Co-Design: Hardware-accelerated systems for graphics and scientific computing, with a focus on efficient 3D Gaussian Splatting (3DGS) rendering and accelerating Incremental Potential Contact (IPC) simulation.
• Machine Learning Systems & LLM for Systems: Efficient training and inference for large-scale machine learning models, including LLM inference optimization, KV-cache management, and system-level optimization. I am also interested in leveraging LLMs for system optimization, code understanding, and automated performance optimization.
• High-Performance Computing: Parallel algorithms and performance optimization for graph and sparse workloads, including graph sparsification, sparse linear algebra, and CPU/GPU parallel computing.

Education

Experieces

Publications and Thesis

• [EDBT 2027] C2: Cache-Conscious Succinct Tries with Adaptive Unary Path Compression
  Kepan Zhang, Tiancheng Zhao, Helen Xu


• [AACL-IJCNLP 2026] LLM Agent Memory: A Survey from a Unified Representation–Management Perspective [pdf]
  Zhenheng Tang, Xin He, Tiancheng Zhao, et. al
  


• [AAAI 2026] OSVBench: Benchmarking LLMs on Specification Generation Tasks for Operating System Verification [pdf]
  Shangyu Li, Juyong Jiang, Tiancheng Zhao, Jiasi Shen


• [HPEC 2025] pdGRASS: A Fast Parallel Density-Aware Algorithm for Graph Spectral Sparsification [pdf]
  Tiancheng Zhao, Zekun Yin, Huihai An, Xiaoyu Yang, Zhou Jin, Jiasi Shen, Helen Xu
  Best Student Paper Award


• [Briefing in Bioinformatics 2024] ifDEEPre: large protein language-based deep learning enables interpretable and fast predictions of enzyme commission numbers [html]
  Qingxiong Tan, Jin Xiao, Jiayang Chen, Yixuan Wang, Zeliang Zhang, Tiancheng Zhao, Yu Li

Honors

Teaching Assistant