Work for a Member company and need a Member Portal account? Register here with your company email address.

Past Member

Kai Hu

Former Graduate Student

Contact Information:

kaihu@media.mit.edu

Groups

City Science

Kai is a visiting Ph.D. candidate at the School of Architecture, South China University of Technology. He is now working with the City Science group at MIT Media Lab.

With a solid background in urban planning practice and the application of artificial intelligence in urban contexts, Kai's current research focuses on case-based design system for urban planning and humanized agent-based model for urban simulation.

He is the principal contributor to the CityFlow project, a low-code development environment enhanced with large language models, aimed at helping urban researchers build expert workflows to address city problems.

Project Research

CityFlow: An Advanced Case-based Design System Integrated with Expert Workflow and LLM Retriever

CityFlow is a versatile tool that allows users to design, evaluate, and visualize urban solutions through an llm-integrated, case-based sys…

Project Research

Graph RAG as Human Choice Model: Building a Data-Driven Simulation Framework with LLM Agents

The study of human behavior in urban environment is an important field in city sciences. However, it's usually not easy to collect behavior…

Project Research

Human-AI Collaborative Planning Method for Incremental Urban Transformation

COVID-19 pandemic served as a catalyst for reimagining urban spaces and emphasized the need for walkable, life-work balanced coummunities.&…

Publication Research

Evolvable case-based design: An artificial intelligence system for urban form generation with specific indicators

Liu, Y., Hu, K., & Deng, Q. (2023). Evolvable case-based design: An artificial intelligence system for urban form generation with specific indicators. Environment and Planning B: Urban Analytics and City Science, 0(0). https://doi.org/10.1177/23998083231219364