- InstructFLIP: Exploring Unified Vision-Language Model for Face Anti-spoofing, ACM MM 2025
- ReCorD: Reasoning and Correcting Diffusion for HOI Generation, ACM MM 2024
- Dual Memory-guided Probabilistic Model for Weakly-supervised Anomaly Detection, IJCAI Workshop 2024
- Learning Efficient Interaction Anchor for HOI Detection, ICME 2024
- Lightweight Deep Learning: An Overview, IEEE Consumer Electronics Magazine 2022
- Heterogeneous Federated Learning through Multi-branch Network, ICME 2021
- Awards:
- Member of the Phi Tau Phi Scholastic Honor Society, 2025
- Hon Hai Technology Award, 2025
- Best Paper Award, 2024
- Lam Research Paper Award and Outstanding Student Scholarship, 2024
Research Experience
- Member of the AIMM group, focusing on lightweight deep learning, knowledge distillation, and federated learning
- Currently broadening research scope to include text-to-image generation and visual language models
Education
- Master's Degree: National Taiwan University, Department of Computer Science, Advisors: Prof. Wen-Huang Cheng and Prof. Hong-Han Shuai, 2021-present
- Bachelor's Degree: National Yang Ming Chiao Tung University, Undergraduate Honors Program in Electrical Engineering and Computer Science, before 2021
- Exchange Experience: RWTH Aachen University, Germany, April to September 2021
Background
- Research Interests: Convergence of computer vision and deep learning
- Background: Kang-Yang (Albert Huang) obtained his MSc degree in Computer Science at National Taiwan University, where he is part of the AIMM group. He previously earned his B.S. degree from the Undergraduate Honors Program in Electrical Engineering and Computer Science at National Yang Ming Chiao Tung University, Taiwan. Additionally, he was an exchange student at RWTH Aachen University, Germany, from April to September in 2021.