Wuao Liu (刘武傲)

I am a first-year Ph.D. student in Computer Science at UMass Amherst, where I am advised by Prof. Grant Van Horn. During my Ph.D. study, I also work closely with Prof. Subhransu Maji and his students.

I have been fortunate to collaborate with top research labs as an intern. In summer 2021, I worked alongside Prof. Mingyang Sun and Dr. Peilin Zhao at Tencent AI Lab.

Previously, I received my M.S. in Robotics at University of Michigan. I worked with Prof. Jason Corso on audio-visual learning and some fancy AR/VR stuff. Before that, I got my B. Eng in Automation from Zhejiang University.

I'm actively looking for research engineer / machine learning engineer internships during summer 2025. Please feel free to contact me!

Email: [first name][last name][at]umass[dot]edu
CV  /  Linkedin  /  Google Scholar  /  Github  /  X

profile photo
The photo was taken in the Mount Sugarloaf State Reservation, MA.

News

  • [2024.9] I will be joining UMass Amherst as a CS PhD student.
Show/Hide old news
  • To be updated ...

Research

My research leverages computer vision and audio processing to build real-world machine learning systems for applications in AR/VR, biodiversity and conservation problems. I'm also interested in exploring the potential of large language models(LLMs) to further enhance these capabilities.

Audio Geolocation
Audio Geolocation: An Investigation with Natural Sounds
Mustafa Chasmai, Wuao Liu, Subhransu Maji, Grant Van Horn
Under Review, 2025
project page / pdf

Using a vision-inspired approach, we tackle the novel challenge of predicting the geographic location of audio recordings by leveraging species sounds and multimodal retrieval techniques.

LLMs for Goal-Oriented Tasks
Can Large Language Models Reason About Goal-Oriented Tasks?
Filippos Bellos, Yayuan Li, Wuao Liu, Jason J. Corso
ACL Workshop, 2024
project page / video / pdf

We study how well LLMs can complete a sequence of steps to achieve a certain goal, such as making a sandwich or repairing a bicycle tire.

Last update: Dec. 2024

Thanks to Jon Barron for providing this amazing template.
Thanks to my friend Xiaofeng Lin for his help building this webpage.