Mengyu Yang
Machine Learning PhD Student at Georgia Tech
About Me
Hi! I’m a Machine Learning PhD student at Georgia Tech working with James Hays. I received my BASc in Engineering Science with Honours from the University of Toronto, where I specialized in Machine Intelligence. I’ve interned at Dolby during Summer 2025 working on multimodal representation learning with spatial audio and Google Research during Fall 2023 working on audio-visual sound source localization.
Here’s my CV.
Research Interests
I’m interested in multimodal learning grounded in computer vision, mainly working at the intersection of vision, audio, and language.
Topics include:
- Representation learning
- Video understanding
- Audiovisual localization
Publications
(2025).
Clink! Chop! Thud! - Learning Object Sounds from Real-World Interactions.
ICCV 2025.
(2023).
The Un-Kidnappable Robot: Acoustic Localization of Sneaking People.
ICRA 2024.
(2021).
TriBERT: Human-centric Audio-visual Representation Learning.
NeurIPS 2021.
(2021).
Soloist: Generating Mixed-Initiative Tutorials from Existing Guitar Instructional Videos Through Audio Processing.
CHI 2021.
(2020).
Mask-Guided Discovery of Semantic Manifolds in Generative Models.
NeurIPS 2020 Creativity Workshop.
(2020).
Musical Speech: A Transformer-based Composition Tool.
NeurIPS 2020 Demonstration Track.