Hi! I’m Kuang-Ming Chen (陳光銘), currently a graduate student at the University of Washington, where I work in the Information Processing Lab under the supervision of Prof. Jenq-Neng Hwang. My current research focuses on Vision-Language Models (VLMs) Understanding, particularly how to align and interpret multimodal information effectively.

Before this, I completed my undergraduate studies at National Taiwan University, advised by Prof. Hung-yi Lee. My previous work involved training pipelines for Large Language Models (LLMs) and self-supervised learning for speech models, with a strong interest in making foundation models more accessible and efficient for real-world applications.

You’ll find information about my publications, research projects, teaching experiences, and more throughout this site.

Thanks for visiting!