I spend my days teaching machines to see into the future. As a recent Computer Science PhD graduate from NTUST (Taiwan Tech), my work in the SPML Lab centers on a singular challenge: How can we make AI perceive complex human environments in real-time? My research focuses on Spatio-Temporal Deep Learning and Multimodal AI (Vision-Language Models), bridging the gap between high-level architectural design and efficient edge-AI deployment, I’m driven by the goal of making autonomous systems safer through smarter spatio-temporal reasoning.

The best ideas don’t always happen behind a monitor

My mental reset is found in the fluid dynamics of motion—whether it’s the split-second intuition of surfing the wase in Yilan, carving through the narrow streets of Taipei on my skateboard, or developing virtual worlds in Unreal Engine. These moments of “flow state” help me wind down from my work and provide the essential ignition for my creativity.

Work Experience

• Research Assistant - Taiwan Tech (NTUST) Oct. 2020 - Jan. 2026

  Reaseach Areas: Multi-modal (text-visual) models, spatio-temporal modelling, image-to-video adaptation, parameter-efficient training, domain adaptation, real-time deployment (NVIDIA Jetson Nano), and self-supervised learning.

  Technologies: PyTorch, Python, C/C++, CUDA, TensorRT, VLM, ViTs, LLMs, GNNs.

• Teaching Assistant - Taiwan Tech (NTUST) Feb. 2021 - Jan. 2026

  Courses: Intelligent Video Surveillance Systems, Database, Large Language Models and Applications.

  Mentoring: Master’s student at our lab (research and code review).

• Junior Researcher - NTIS Research Centre Sept. 2019 - Sept. 2020

  Patented Innovation: Co-invented a multi-modal biometric approach (US Patent 2025/0184148) for person identification based on short audio-visual recordings.

  Full-Stack Architecture: Integrated a C++ backend (OpenCV/DLib with CNNs) and a Node.js server to bridge AI-generated hashes as a simple QR code to a web UI for real-time person authorization.

• Research & Software Engineer -- Palaxo International Ltd. Sept. 2017 - Sept. 2020

  Researched and developed an image analysis system for paperless documents to allow text recognition and automatically anonymize sensitive data (using Tesseract-OCR / OpenCV / DLib / C++).

• Software Engineer - Kerio Technologies, Inc. Jun. 2016 - Jun. 2017

  Implementing manageable router with security (firewall) and optimization using own kernel in C/C++.

Education

• Ph.D. in Computer Vision & Deep Learning - Taiwan Tech (NTUST), ECE Department Oct. 2020 - Feb. 2026

  Reaseach Topic: Efficient Spatio-Temporal Deep Learning for Real-Time Video-Based Accident Anticipation and Understanding on Edge Devices

  Advisors: prof. Yie-Tarng Chen and Wen-Hsien Fang

• M.Sc. in Software Engineering - University of West Bohemia (UWB), CSE Department Sept. 2017 - Jun. 2020

  Thesis: Information Extraction from Heterogeneous Image-based Documents using Templates

  Advisor: asst. prof. Kamil Ekštein, M.Sc., Ph.D.

• Master’s Exchange Programme - Taiwan Tech (NTUST), CSIE Department Sept. 2018 - Feb. 2019

  Courses: Intelligent Video Surveillance Systems, Intelligent Control System, Basic Oral Chinese

• B.Sc. in Software Engineering - University of West Bohemia (UWB), CSE Department Sept. 2014 - Jun. 2017

Honors & Awards

1. IT SPY 2020 – Recognized as one of the best Master’s theses in Central Europe submitted in 2020.
2. M.Sc. Diploma with Honors.
3. Recipient of the Taiwan Ministry of Education Scholarship (2020–2024).
4. EMI (English as a Medium of Instruction) Teaching Certificate.