Hi! I am a Ph.D. candidate at the Univeristy of British Columbia (UBC) and the Vector Institute for AI advised by Vered Shwartz and Raymond NG in the Natural Language Processing group. I frequently collaborate with Leonid Sigal in the Computer Vision group.

My research focuses on enabling models to reason about the visual world beyond what is explicitly shown, similar to how humans build mental models. I study how Vision-Language Models (VLMs) infer implicit information such as object properties, spatial relations, and causal event dynamics. Currently, I am investigating how models update their internal beliefs when they encounter surprising events in video streams.

During my PhD, I have had the opportunity to intern at industry research groups, including FAIR (Meta), Microsoft Research in Summer 2024 and Meta Reality labs in Summer 2023.