Simon Fraser University

ZhuoCodyNing

I build generative models that make video and sound together.

About

Portrait of Zhuo (Cody) Ning

I'm a PhD student in Computing Science at Simon Fraser University, working with Ali Mahdavi-Amiri.

My research is on joint audio-video generation: getting a model to produce a scene where every sound belongs to something you can see. Before that I worked on texture generation.

Alongside research, I work as a software architect at UBC, designing large-scale systems.

Publications

Generated lab scene with a scientist, an android, a dog and a cat

arXiv, 2026

Soundwich: Video Generation with Layered and Controllable Audio

Zhuo Ning, AmirHossein Naghi Razlighi, Sagi Polaczek, Daniel Cohen-Or, Ali Mahdavi-Amiri

PaperCodeProject page
A pirate and a parrot in four steering variants

arXiv, 2026

The Attention Triangle in Audio-Video Models

Sagi Polaczek, Noa Kraicer, Gal Metzer, Zhuo Ning, Ali Mahdavi-Amiri, Daniel Cohen-Or, Raja Giryes

Paper