I am a Ph.D. candidate in Urban Science at MIT, advised by Professor Andres Sevtsuk. My independent dissertation research, Seeing HAI, develops computational methods for observing human activities and interactions on sidewalks and pedestrian spaces. I combine geo-referenced imagery and video with computer vision, vision-language models, and spatial analysis to study sidewalk life, pedestrian behavior, and public life across cities. Alongside this research, I contribute to collaborative projects at the City Form Lab on pedestrian flow and social activity in public space.
My research has also been shaped by experiences across academia, industry, and professional practice. As an Applied Scientist Intern at Amazon, I worked on multimodal machine learning for reasoning evaluation at AGI and cross-modal video retrieval at AWS. As a Visiting Researcher at UCLA’s Vision and Autonomy Intelligence Lab, I contributed to the 2D semantic component of a sidewalk-robot perception project. Before returning to MIT, I founded CitoryTech, an urban visual AI studio, where I led more than twenty research and consulting projects for organizations including the World Bank, Daimler, Tencent, and city governments.
My work has appeared in AAAI, Nature Cities, Cities, and ECCV. Google Scholar recorded 1,764 citations to my work as of August 2026. I have led funded research as principal investigator, including projects supported by the U.S. ACCESS program and China’s National Key R&D Program. A City Form Lab collaboration that I lead at MIT was exhibited at the 2025 Venice Architecture Biennale. I have also served as a teaching assistant and guest lecturer at MIT, NYU, Tongji University, and the University of Hong Kong, teaching and supporting courses in urban design, GIS, spatial analysis, urban data science, and computer vision for urban studies.