Skip to content

Research

ArchSeek: Retrieving Architectural Case Studies Using Vision-Language Models

⚑ LLM for design⚑ Information retrieval
Danrui Li, Yichao Shi, Yaluo Wang, Ziying Shi, Mubbasir Kapadia.
CAAD Futures 2025

Search for architectural case studies using natural language queries, images, or just a few mouse clicks.

>>
Displayed Image

From Words to Worlds: Transforming One-line Prompts into Multi-modal Digital Stories with LLM Agents

⚑ LLM for design⚑ Digital storytelling
Danrui Li, Samuel S. Sohn, Sen Zhang, Che-Jui Chang, Mubbasir Kapadia.
ACM SIGGRAPH Conference on Motion, Interaction, and Games (MIG 2024)

Utilizing Large Language Models as an organizer of various generative tools, the StoryAgent framework automates digital storytelling with fine-grained control over intermediate products.

>>>
Displayed Image

Microscopic modeling of attention-based movement behaviors

⚑ Human behavior modeling⚑ Pedestrian simulation
Danrui Li, Mathew Schwartz, Samuel S. Sohn, Sejong Yoon, Vladimir Pavlovic, Mubbasir Kapadia (2024)
Transportation Research Part C: Emerging Technologies

How will attention affect walking speed in retail areas? We model how pedestrians will be attracted to environmental objects and how this will slow down their walking speed. Then we show how our model can help optimize the design of retail areas in transportation hubs.

>>
Displayed Image

TrajDiffuse: A Conditional Diffusion Model for Environment-Aware Trajectory Prediction

⚑ Human behavior modeling⚑ Trajectory prediction
Qingze(Tony) Liu, Danrui Li, Samuel S. Sohn, Sejong Yoon, Mubbasir Kapadia, Vladimir Pavlovic.
Accepted by 2024 International Conference on Pattern Recognition (ICPR)

We form the trajectory prediction problem as a denoising impaint task and design a map-based guidance term for the diffusion process. TrajDiffuse is able to generate trajectory predictions that match or exceed the accuracy and diversity of the SOTA, while adhering almost perfectly to environmental constraints.

>
Displayed Image

Learning from Synthetic Human Group Activities

⚑ Human behavior modeling⚑ Synthetic data
Che-Jui Chang, Danrui Li, Deep Patel et al. (2024)
CVPR 2024

A synthetic data generator for multi-view multi-group multi-person human atomic actions and group activities, which facilitates the learning of human-centered tasks across single-person, multi-person, and multi-group conditions.

>>
Displayed Image

Influence of Security Check Procedures on Transfer Efficiency from Railway Stations to Subways

⚑ Human behavior modeling⚑ Architecture design⚑ Pedestrian simulation
Yu Zhuang, Danrui Li (2024)
Journal of Tongji University

The influence of arriving passengers and the interaction effects between external factors are compared in two scenarios: the mutual recognition of security checks and the application of face recognition systems.

>

How Do Retail Stores Affect Pedestrian Walking Speed?

⚑ Human behavior modeling
Danrui Li
Traffic and Granular Flow 2022

A detailed empirical observations that focus on pedestrian speed variations and their dynamics in front of stores.

>

Sensitivity Analysis of Pedestrian Simulation on Train station platforms

⚑ Human behavior modeling⚑ Architecture design⚑ Pedestrian simulation
Danrui Li, Rong Huang, Yihao Wu
CAADRIA 2021

Which parameters are most sensitive, thus most important to calibrate, in pedestrian simulation models on train station platforms? We conduct a sensitivity analysis to answer this question.

>

Quantification and Typology Methods for Spatial Regionalism

⚑ Architecture design
Danrui Li, Yihao Wu, Liuqing Wu
CAADRIA 2021

We propose a method to quantify spatial regionalism and a typology to classify different types of spatial regionalism.