Zhuo (Cody) Ning

PhD student in Computing Science at Simon Fraser University, in the GrUVi Lab, advised by Prof. Ali Mahdavi-Amiri.

I work on generative models for video and sound, and on how the two shape each other: how what we see decides what we hear, and how sound can drive what moves on screen. Earlier, I worked on texture generation. I am also a software architect at UBC.

Papers

A generated scene in a dim drawing room: a woman at a table, two men standing, a man at the piano and a trumpeter
One generated scene with nine separate audio stems, one for each sound source.

Soundwich: Video Generation with Layered and Controllable Audio

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

arXiv, 2026

A pirate and a parrot in four variants, showing how steering attention changes who speaks
Steering attention changes which character speaks.

The Attention Triangle in Audio-Video Models

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

arXiv, 2026

Contact