Portrait of Chih-Wei Tseng

Chih-Wei Tseng

Research Assistant • Institute of Electrical and Control Engineering@NYCU

I am a Research Assistant at National Yang Ming Chiao Tung University (NYCU), supervised by Chair Professor Bing-Fei Wu. My research focuses on generative, efficient, and interpretable AI for intelligent robotic systems (including autonomous driving) and remote physiological sensing.

Recent work includes interpretable memory-based trajectory planning (winning the innovation award on the Autonomous Grand Challenge 2025 (ICCV Phase)); Generative AI for the synthesis of rare-event scenarios in autonomous driving; and an industry collaboration on interpretability for imaging-to-rPPG. I also lead several master’s students on generative AI for autonomous-driving scenarios and rare-event data. During my M.S., I developed a contact-free rPPG-based atrial fibrillation detection system that runs in real time on mobile devices and achieves >90% accuracy under motion and lighting variations; this work was selected as a Feature Article published in IEEE JBHI.

View my CV · View Publications

Selected Publications

TIP-C2: A Training-Free Interpretable Module for Generation Error Detection via Principal Component Analysis and Conditional Mutual Information

C.-H Lee, C.-W Tseng, C.-W Sun, B.-F. Wu

ICML
Status: Under Review

Paper (Submitted)

CoSMIC: Cognitively-Inspiration System with Memory interpretability and Consolidation for trajectory planning in Autonomous Driving

C.-W Sun, C.-W. Tseng, Yu-Chen Lin, and B.-F. Wu

IEEE Transactions on Intelligent Transportation Systems (IEEE T-ITS)
Status: Under Review

Paper (Submitted)
JBHI Feature Article thumbnail

A Real-Time Contact-Free Atrial Fibrillation Detection System for Mobile Devices

(Feature Article)

C.-W. Tseng, B.-F. Wu, S. Yu

IEEE Journal of Biomedical and Health Informatics (IEEE JBHI), Jan. 2025

View Paper