I completed my B.Sc. in Computing Science with Distinction at Simon Fraser University, where I work with Angelica Lim at Rosie Lab on real-time non-verbal human–robot interaction, and previously with Ke Li at APEX Lab on text-conditional generative models. Before SFU, I interned at Huawei on real-time acoustic echo cancellation, which grew into my first-author paper at Interspeech 2025.
I’m interested in world models that simulate the world through an explicit, shared state grounded in the scene’s 3D layout, its physical properties, and the goals of the agents within it. In the long term, I want to build an AI director that acts on this state, orchestrating events and interactions in the simulated world and using its interventions to learn the world’s causal structure.