My name is Liang-Yuan “Leo” Wu 吳兩原. I am now working with Prof. Dhruv “DJ” Jain and the Soundability Lab at the AI Laboratory, University of Michigan CSE. I recently graduated with a Master’s Degree in Computer Science & Engineering from the University of Michigan.

I’m a researcher and engineer working at the intersection of Human-Computer Interaction (HCI) and Artificial Intelligence (AI), with a focus on building human-centered technologies that make sound and speech more accessible. My work often involves close collaboration with the Deaf and Hard of Hearing (DHH) community to explore how people perceive, trust, and engage with audio AI.

My recent work includes, (1) using large multimodal models to interpret auditory scenes and generate personalized sound descriptions, (2) improving captioning quality with large language models (LLMs), and (3) exploring captioning usage in constrained environments such as clinical communication.

I have hands-on experience in software development, with a background in deep learning, audio and language processing, and full-stack development. I also bring experience in UX research, including mixed-methods evaluation with users. Currently, I’m exploring research and industry opportunities in audio AI and human-centered machine learning. I’m always excited about new collaborations and conversations, please feel free to reach out!

Resume / CV