I am a fourth-year Ph.D. student in the School of Electronic Science and Engineering, Nanjing University, under the supervision of Prof. Yun Li, Prof. Qiong Chang, and Prof. Jun Miyazaki. I was admitted directly to the Ph.D. program after receiving my B.Eng. degree from Nanchang University via a merit-based recommendation and exemption from the national graduate entrance exam.
My research focuses on high-performance parallel algorithm design on GPUs, aiming to accelerate core computational tasks in computer vision, graph analytics, and large-scale data processing. Specifically, I target desktop, server, and embedded GPUs to design algorithms that are highly parallel, computationally efficient, and resource-aware, by considering both algorithmic structure and GPU architectural characteristics.
News
| Oct 2025 | Join the Miyazaki Lab, Institute of Science Tokyo, as a Visiting Junior Fellow under the support of the China Scholarship Council (CSC). |
| Jun 2025 | A paper "3D GNLM: Efficient 3D Non-Local Means Kernel with Nested Reuse Strategies for Embedded GPUs" is accepted to TACO. |
| May 2025 | Receive a scholarship from the China Scholarship Council (CSC) for joint Ph.D. training. |
| Feb 2025 | Visit Miyazaki Lab, Institute of Science Tokyo, as a Visiting Junior Fellow. |
| Jan 2025 | A paper "Efficient Parallel Implementation of Non-Local Means Algorithm on GPU" is accepted to GPGPU'25. |
| Aug 2024 | A paper "An Optimized GPU Implementation for GIST Descriptor" is accepted to TACO. |
| Mar 2023 | A paper "Multi-directional Sobel operator kernel on GPUs" is accepted to JPDC. |
Publications
| TACO | 3D GNLM: Efficient 3D Non-Local Means Kernel with Nested Reuse Strategies for Embedded GPUs Xiang Li, Qiong Chang, Yun Li, Jun Miyazaki |
| TECS | Faster than Fast: Accelerating Oriented FAST Feature Detection on Low-end Embedded GPUs Qiong Chang, Xinyuan Chen, Xiang Li, Weimin Wang, Jun Miyazaki |
| GPGPU'25 | Efficient Parallel Implementation of Non-Local Means Algorithm on GPU Xiang Li, Qiong Chang, Yun Li, Jun Miyazaki |
| TACO | An Optimized GPU Implementation for GIST Descriptor Xiang Li, Qiong Chang, Aolong Zha, Shijie Chang, Yun Li, Jun Miyazaki |
| JPDC | Multi-directional Sobel Operator Kernel on GPUs Qiong Chang, Xiang Li, Yun Li, Jun Miyazaki |
| ICRA 2023 | StereoVAE: A Lightweight Stereo-Matching System Using Embedded GPUs Qiong Chang, Xiang Li, Xin Xu, Xin Liu, Yun Li, Jun Miyazaki |
Education
| 2022–present | Ph.D. Student, School of Electronic Science and Engineering, Nanjing University, China. |
| 2018–2022 | B.E., Institute for Advanced Study, Nanchang University, China. |
Experience
| Feb 2025–Apr 2025 | Visiting Junior Fellow, Department of Computer Science, School of Computing, Institute of Science Tokyo, Japan. |
Academic Service
| 2025–present | Reviewer, ACM Transactions on Architecture and Code Optimization (TACO). |
| 2025–present | Reviewer, The Journal of Supercomputing (TJSC). |
