Assistant Professor at NYCU Institute of Artificial Intelligence Innovation. Pioneering research in Computer Vision, Generative AI, and Robotic AI — bridging the gap between intelligent systems and real-world automation. Former Data Scientist & Team Lead at TSMC.
Scholar, engineer, and builder of perceptive machines.
I am an Assistant Professor at the Institute of Artificial Intelligence Innovation, National Yang Ming Chiao Tung University (NYCU), Taiwan, where I lead research at the intersection of computer vision, generative AI, and robotic intelligence.
Prior to academia, I spent 17 years at TSMC (2006–2023) as a Data Scientist and Team Lead, where I drove AI adoption for semiconductor manufacturing — developing state-of-the-art deep learning systems for defect inspection, yield prediction, and robotic automation.
My mission is to build intelligent machines that perceive, reason, and act in complex real-world environments, with a focus on bridging simulation and reality.
Three interleaved threads — perception, generation, and embodiment.
Developing 2D and 3D foundation models for robust perception. Our work spans object detection, instance segmentation, depth estimation, and dense 3D scene reconstruction — with applications in smart manufacturing and autonomous systems.
Harnessing diffusion models and generative architectures to create digital twins, synthesize training data, and model complex industrial processes. Bridging the gap between simulation and physical reality through learned generative representations.
Building robots that see, understand, and act. Our research combines reinforcement learning, vision-language models, and sim-to-real transfer to create intelligent agents capable of complex manipulation and navigation in unstructured environments.
From silicon to students — an industry-to-academia arc.
Graduate courses taught at the Institute of Artificial Intelligence Innovation, NYCU.
This course aims to provide students with a deep understanding of the fundamental concepts and techniques of computer vision, including image formation, feature extraction, 3D reconstruction, image segmentation, object recognition, deep learning, object detection, object tracking, and facial recognition. It also aims to equip students with the implementation and application of algorithms, models, and frameworks related to computer vision, enabling them to address computer vision problems across various domains such as autonomous driving, smart homes, medical image analysis, and more. Through this course, students will comprehend the limitations and challenges of current computer vision applications and explore future development directions. By undertaking this course, students will acquire the following abilities:
| Wk | Date | Topic | Slides | Homework | Notes |
|---|---|---|---|---|---|
| 1 | 2/18 | Course Introduction | Lec0 Lec1 | ||
| 2 | 2/25 | CV Introduction / Image Formation | Lec2 | ||
| 3 | 3/4 | Intensity Transformation | Lec3 | HW1: Image Sensing Pipeline | |
| 4 | 3/11 | Edge Detection | Lec4 | Group Form Due | |
| 5 | 3/18 | Corner Detection | Lec5 | HW1 Due | |
| 6 | 3/25 | Line Detection | Lec6 | HW2: Harris Corner Detection | |
| 7 | 4/1 | Camera Calibration | Lec7 | ||
| 8 | 4/8 | Midterm Report | HW2 & Midterm Report Due | ||
| 9 | 4/15 | Image Segmentation | Lec8 | HW3: Camera Calibration | |
| 10 | 4/22 | Special Lecture | |||
| 11 | 4/29 | Object Detection | Lec9 | HW3 Due | |
| 12 | 5/6 | Deep Image Segmentation | Lec10 | HW4: Image Segmentation | |
| 13 | 5/13 | Image Classification | Lec11 | ||
| 14 | 5/20 | VLM / LLM | Lec12 | HW4 Due | |
| 15 | 5/27 | 3D Vision | Lec13 | ||
| 16 | 6/3 | Final Project Presentation | Final Report Due |
This course provides students with a comprehensive introduction to the fundamentals of Generative Artificial Intelligence (GenAI), with a particular focus on image synthesis. It is designed to cultivate both theoretical understanding and practical implementation skills, while encouraging students to critically examine the applications of GenAI across diverse domains. By engaging with state-of-the-art models and techniques, students will explore the current limitations and challenges of GenAI, as well as emerging research trends and potential future directions in image generation.
To strengthen the connection between theory and practice, the course features joint instruction with Dr. Chia-Min Cheng, Senior Expert from AI Technology Division of MediaTek, who will share cutting-edge industry insights. His lectures will bridge academic concepts with real-world product development, highlighting both technical challenges and commercial opportunities.
| Wk | Date | Topic | Slides | Homework | Notes |
|---|---|---|---|---|---|
| 1 | 9/4 | Class Introduction and Overview | Lec0 | ||
| 2 | 9/11 | Introduction of GenAI | Lec1 | ||
| 3 | 9/18 | Overview of Vision Generative Models | Lec2 | ||
| 4 | 9/25 | Autoencoder | Lec3 | Group Form Due | |
| 5 | 10/2 | Basic Principles and Concepts of GANs | Lec4 | HW1 | |
| 6 | 10/9 | Applications and Developments of GANs | Lec5 | ||
| 7 | 10/16 | Basic Principles and Concepts of DMs | Lec6 | HW1 Due | |
| 8 | 10/23 | Special Lecture | |||
| 9 | 10/30 | Midterm Report | |||
| 10 | 11/6 | Applications and Developments of DMs | Midterm Report Due | ||
| 11 | 11/13 | 3D Vision | Lec7 | HW2 | |
| 12 | 11/20 | GenAI Application in Industry — Mobile, Automotive, AR/VR | Lec8 | ||
| 13 | 11/27 | 3D Visual Effects | Lec9 | HW2 Due | |
| 14 | 12/4 | Mixed Reality | Lec10 | ||
| 15 | 12/11 | VLM & LMM | Lec11 | ||
| 16 | 12/18 | Final Project Presentation | Final Report Due |
This course, Artificial Intelligence (IIAI30017), offers students a comprehensive introduction to the fundamental concepts, techniques, and applications of artificial intelligence (AI). Through lectures, programming assignments, literature reviews, and project-based learning, students will gain both theoretical understanding and practical skills in AI.
| Wk | Date | Topic | Slides | Homework | Notes |
|---|---|---|---|---|---|
| 1 | 9/2 | Class Introduction and Overview | Lec0 | ||
| 2 | 9/9 | Introduction of Artificial Intelligence / Python Tutorial | Lec1 | ||
| 3 | 9/16 | Informed Search | Lec2 | ||
| 4 | 9/23 | Evolutionary Algorithms 1 | Lec3 | HW1: Greedy Best-First Search | Group Form Due |
| 5 | 9/30 | Evolutionary Algorithms 2 | |||
| 6 | 10/7 | Local Search Methods | Lec4 | HW1 Due | |
| 7 | 10/14 | Swarm Intelligence 1 | Lec5 | HW2: GA | |
| 8 | 10/21 | Swarm Intelligence 2 | |||
| 9 | 10/28 | Midterm Report | HW2 Due | ||
| 10 | 11/4 | Neural Networks | Lec6 | Midterm Report Due | |
| 11 | 11/11 | Convolutional Architecture | Lec7 | ||
| 12 | 11/18 | Training Neural Networks 1 | Lec8 | HW3: Neural Networks | |
| 13 | 11/25 | Training Neural Networks 2 | |||
| 14 | 12/2 | 3D Vision | Lec9 | HW3 Due | |
| 15 | 12/9 | Final Project Presentation | |||
| 16 | 12/16 | Special Lecture | Final Report Due |
Peer-reviewed papers, journal articles, and competition entries — in reverse chronological order.
Selected distinctions and service roles.
Open to collaborations, student applications, and speaking invitations.
I am actively recruiting graduate and doctoral students passionate about AI, robotics, and computer vision. If you are interested in joining the ROSSI Lab or collaborating on research, feel free to reach out.