蔡雨轩 · PhD · University of North Carolina at Chapel Hill · City & Regional Planning
"The city is kind of vast and we still have so much to say to each other"
— François Périer to Giulietta Masina
_
Yuxuan Cai
00 · About
[ PHOTO ]
Teaching machines to sense the city
I am a PhD student in City and Regional Planning at University of North Carolina at Chapel Hill. Previously I completed my MA in Computational Social Science at the University of Chicago and studied architecture at UC Berkeley.
My research sits at the intersection of urban planning, AI interpretability, and public health — probing how vision-language models encode urban perception, and building LLM multi-agent frameworks that model planning decision-making, behavioral bias, negotiation, and intent alignment in urban contexts.
PositionPhD Student, University of North Carolina at Chapel Hill
Understanding how humans experience urban environments through crowdsourced data, street-view imagery, and social media — and how AI systems represent these perceptions.
VLM / CLIPStreet ViewNLPUrban Cognition
02
LLM Planning Simulation & Decision-Making
Building LLM multi-agent frameworks that model planning decision processes — including behavioral bias, intent understanding, negotiation dynamics, and alignment in urban policy contexts.
Long-term environmental exposures — air pollution, heat, green space inequality — and their disparate effects on health outcomes across demographic groups.
Env. HealthGISML / DLEquity
02 · Publications
Selected papers
2026
Evaluating the Spatial-Temporal Impact of Urban Nature on Urban Vitality in Vancouver: A Social Media and GPS Data Approach
Land Use Policy
Huang, Y., Du, J., Chen, M., Lin, Y., Huang, S., & Cai, Y.