‘Science plus arts multiplied by faith then divided by the number of our ethnic race.’ — Nujabes, feat. Shing02, Luv(sic) pt2
About Myself
I am an AI/Graphics/Robotics Researcher with international research experience specializing in Physics-informed Machine Learning, Reinforcement Learning, and Graph Learning. Currently pursuing my Master's degree at National Taiwan University, advised by Prof. Bing-Yu “Robin” Chen.
My recent research interests span across 4 core areas: 1. Numerical Optimization in Graphics and Vision (neural PDE solvers, differentiable physical simulation, dynamics, HPC), 2. Robotics (Sim2Real transfer, robotic manipulation and assembly, motion planning), 3. Multimodal Foundation Models (MLLMs, multi-agent systems, GenAI, federated learning, sensing), and 4. Creative 2D/3D Geometry (digital twins, animation, CAD, and gaussian splatting). Welcome for any potential collaborations!
I have gained international research experience through internships and collaborations at RIKEN Japan, Center for Computational Science (R-CCS) (Large-Scale Digital Twin Research Team @Kobe/Osaka, Japan; Team Principal Prof. Hirozumi Yamaguchi (Osaka University)), MoonShine Animation Studio (R&D; Dir. Shaune Jan; collaborated advisors Prof. Xiang “Anthony” Chen (UCLA), Prof. Yu-Lun “Alex” Liu (NYCU)), and Delta Electronics.
I also worked closely with multiple academic groups during my undergraduate studies and published 8 conference papers in top-tier AI/CS conferences: Urban Science & Computing Lab led by Prof. Hsun-Ping Hsieh, and RAC-Coon (Robot Aided Creation and Construction Research Group) with Prof. Yang-Ting Shen, Prof. Chia-Ching Yen, and Prof. Wen-Yu Su.
All my projects are available on my GitHub page, spanning generative modeling, multi-agent RL, multimodal agents, 3D rendering, and intelligent systems. I actively contribute to the research community as a reviewer for premier conferences including ACM CHI, HRI, CSCW, and WWW.
My interests: graffiti (in legal area), live house/music festival, traveling.
Publications
Selected (2)
Others (6)
Thesis
Research & Work Experience
High-Performance Computing Research Intern
RIKEN Center for Computational Science, Kobe/Osaka, Japan — Large-Scale Digital Twin Team (Advisor: Prof. Hirozumi Yamaguchi)
- Large-scale digital twin & multimodal data-fusion sensing (WiFi, point cloud, RGBD) on Fugaku supercomputer.
- Edge/cloud distributed computing with graph federated learning foundation models and differential privacy for human–scene interaction.
Vision Language Models Research Intern
MoonShine Animation Studio — R&D Team (Dir. Shaune Jan; Xiang ‘Anthony’ Chen, UCLA)
- Multi-agent MLLM-as-a-judge (AutoGen) for efficient supervisor review and improved Editable 3DGS production workflows.
Research Assistant (Interactive Graphics Lab)
Communications & Multimedia Lab, National Taiwan University (Advisor: Prof. Robin Bing-Yu Chen)
- Differentiable Projective Dynamics hyper-elastic mesh solver with positive-definite Hessian projection; 1.65×–2.26× acceleration via stable clamping strategies.
Research Assistant
Robot-Aided Creation & Construction Research Group — Synchronization Lab (Prof. Yang-Ting Shen, Prof. Chia-Ching Yen, Prof. Alvin Wen-Yu Su)
- Robotic reinforcement learning on Kuka/UR10/Hiwin in Omniverse Isaac Gym/Lab; graph RL for geometric brick assembly by mobile manipulators.
- ROS2 systems integrating SLAM, supervised learning (YOLO, LSTM), and RL for motion control, planning, and obstacle avoidance.
Deep Learning Intern
Delta Electronics, Inc. — Power and System Business Group
- 3D point cloud generative autoencoder trained over 74k meshes (PyTorch3D, Docker, V100).
- XGBoost for inductance parameter prediction from electromagnetic simulation, reducing MAE to ~1% of formula-based solution.
Honors & Awards
2023 AIoT Innovation Challenge
- Secured 3rd Place & Sponsors Award ($30,000) from NXP Semiconductors (Awards).
- Built a microcontroller-based SensorHub (ADI/NXP/Arduino) integrating DHT11/SCD40/PMS5003T via I²C/UART; developed calibration tests with real-time logging in HVAC/fan/lighting control linked to a Unity digital twin for vision-model-based crowd regulation.
2025 Overseas Conference Travel Grant
- Graduate student travel support recipient ($1,000) for SIGGRAPH Asia 2025.
Academic & Community Service
Association for Computing Machinery Conferences
- ACM CHI’25
- ACM HRI’25
- ACM CSCW’24
- ACM WWW’25
Lead Technical Specialist
NTU AI Club, Taipei, Taiwan
- Led academic initiatives and lectures on multimodal learning and reinforcement learning; mentored undergrads toward accepted submissions.
Mandatory Military Service
Taiwan Air Force