I'm a Master's student in Computer Vision at Carnegie Mellon University, where I work with Prof. Katerina Fragkiadaki on problems at the intersection of robot learning, robotic perception, and 4D generative models. Before CMU, I earned my undergraduate degree in Computer Science and Information Engineering at National Taiwan University, where I was fortunate to be advised by Prof. Winston H. Hsu, Prof. Yi-Ting Chen, and Prof. Tsung-Wei Ke.
Began the ETH Robotics Student Fellowship at ETH Zurich, advised by Prof. Stefan Leutenegger.
"SM4RT" was accepted for publication.
"RobotArena ∞" was accepted for publication.
Began Master's research with Prof. Katerina Fragkiadaki at Carnegie Mellon University.
"VICtoR" was accepted for publication.
Graduated with a B.S. in Computer Science and Information Engineering from National Taiwan University.
"AED" was accepted for publication.
Began undergraduate research on 4D scene reconstruction with Prof. Tsung-Wei Ke.
Began a Data Engineer internship at Genenet Technology Ltd. in the UK.
Carnegie Mellon University · Pittsburgh, PA
National Taiwan University · Taipei, Taiwan
RobotArena ∞ is a scalable framework for benchmarking generalist robot policies: real-world environments are translated into simulation, making large-scale, reproducible evaluation possible.
Existing feed-forward approaches typically treat geometry reconstruction and motion estimation as separate problems, often predicting motion entangled with camera movement. SM4RT instead solves the two sequentially — reconstructing 3D geometry first, then bootstrapping motion estimation from the predicted structure.
Existing Vision-Instruction Correlation (VIC) reward models struggle to train on long-horizon tasks. VICtoR addresses this with a hierarchical reward model built for long-horizon robotic reinforcement learning.
AED formulates the problem of monitoring a few-shot imitation policy's behavior as it acts, and introduces PrObe, a method that learns from the policy's own feature representations to catch errors as they happen.
Jul. 2026 – Aug. 2026
ETH Robotics Student Fellow, Mobile Robotics Lab, ETH ZurichWorking with Prof. Stefan Leutenegger, I explored Real2Sim2Real robot learning — using model-based reinforcement learning to transfer skills from human demonstrations into robotic policies.
Jul. 2024 – Nov. 2024
Data Engineer Intern, Genenet Technology Ltd. UKAs part of the Talent Circulation Alliance's Taiwanese Talent Outbound International Internship, I helped deploy a genetic sequence analysis service and built a video-based system for detecting cardiac organoid beating patterns.
May. 2022 – Jun. 2024
Web Software Developer & Data Analyst, StatsInsightI built the first online platform for Taiwanese baseball scouting and statistical visualization, then used it to support data analysis for teams in the Chinese Professional Baseball League (CPBL) and the Chinese Taipei National Team at the 2023 World Baseball Classic.