2026
Software Engineering Intern
- Android Jetpack (CameraX)
About Me
I'm a fourth-year undergraduate student in Computer Science at National Yang Ming Chiao Tung University, advised by Prof. Tsung-Tai Yeh and Prof. Yu-Lun Liu. I work on efficient computing and computer vision, with a focus on computer architecture for machine learning systems.
Previously, I worked at Google as a Software Engineering Intern. In the coming year, I will be an exchange student at KTH Royal Institute of Technology.
Timeline
2024 - 2026
Team Member
NYCU CS Information Technology Center
- Net, Mail, PC & HPC
2023 - 2027
B.S. in Computer Science
National Yang Ming Chiao Tung University
News
- Jun 2026: Joined Google as Software Engineering Intern
- May 2026: Received Fifth Place at 2026 WildBot Robotics Competition
- Apr 2026: Awarded Academic Excellence Award
- Jul 2025: Received Merit Award at Department Capstone Project Competition
- Jul 2025: Awarded NSTC University Student Research Project Grant
- May 2025: Promoted to Development Team Leader at NYCU CS Student Association
- Feb 2025: Joined NYCU Computational Photography Lab under Prof. Yu-Lun Liu
- Nov 2024: Awarded Academic Excellence Award
Publications
OuroWorld: Bringing Any 3D World Alive as Diverse, Endlessly Looping 3D Cinemagraphs
You-Zhe Xie, Ting-Wei Chou, Yu-Hsuan Li, Kaipeng Zhang, Zhixiang Wang, Yu-Lun Liu
arXiv preprint, 2026
3D world models generate worlds that are frozen in time. OuroWorld brings them alive, endlessly. No masks, no seams: any static 3DGS scene becomes a 3D cinemagraph whose motion loops by construction, from any viewpoint.
Projects
NYCU CS Past Exams
A full-stack platform for archiving and browsing NYCU CS past exams, supporting search and filtering by course, instructor, and year, in-browser PDF/image preview, per-exam discussion forums, and AI-generated practice questions; built with Vue 3, FastAPI, PostgreSQL, Redis, and MinIO
AdaFreeU: Adaptive FreeU Parameter Prediction for Text-to-Image Diffusion Models
An adaptive extension of FreeU that predicts per-prompt scaling parameters for Stable Diffusion using a Gaussian policy trained with REINFORCE and DPO, improving image quality over standard SD and default FreeU
