Mengyu Yang

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'm interested in multimodal learning at the intersection of vision 📷, audio 🎧, and language 💬. Topics include MLLMs for video understanding, representation learning, and audio-visual localization.

I've interned at Dolby working on multimodal representation learning for spatial audio and Google Research working on audio-visual sound source separation and localization.

[Now] I'm currently interning at Adobe, working on dense audio-visual correspondence in MLLMs!