Jiuyi Xu's Homepage

About

Jiuyi (Joey) Xu is a second-year Ph.D. student in Robotics at the Colorado School of Mines under the supervision of Dr. Yangming Shi. His research interests include, but are not limited to, Vision-Language-Action (VLA) models, generative AI (e.g., image generation) and efficient AI (e.g., quantization). He holds an M.S. in Computer Science from the University of Southern California (USC) and a B.E. in Software Engineering from Dalian University of Technology (DLUT). Previously, he was a student research intern at USC’s Institute for Creative Technologies, working on projects related to open-vocabulary object detection (OVOD) and open-vocabulary semantic segmentation (OVSS). Beyond research, Joey is an active peer reviewer for the Journal of Computing in Civil Engineering and has contributed to multiple academic conferences/journals. He is also a student member of IEEE, ACM, and ASCE. In his spare time, he really likes going to the gym and playing basketball.

Publications

Xu, J., Jin, Q., Chen, M., Feng, A., Sui, Y., Shi, Y. (2025). "LowDiff: Efficient Diffusion Sampling with Low-Resolution Condition." Under Review.
Vahidi, M., Xu, J., Shi, Y., & Liu, K. (2025). "Domain Knowledge-Infused Prompting for Deep and Full-Sentence Information Extraction from Bridge Inspection Reports." Under Review.
Xu, J., Sanni, T., Liu, Z., Ye, Y., Lee, J., Song, W., Shi, Y. (2025). "To Shelter or Not To Shelter: Exploring the Influence of Different Modalities in Virtual Reality on Individuals' Tornado Mitigation Behaviors." Under Review.
Xu, J., Kim, R., Ye, Y., & Shi, Y. (2025). "An Autoregressive-based Framework for Simulating Stochastic Occupant Behavior in Residential Buildings." Building Simulation.
Xu, J., Chen, M., & Shi, Y. (2025). "GenVision: Enhancing Construction Safety Monitoring with Synthetic Image Generation." Winter Simulation Conference 2025.
Chen, M., Leal, L., Hu, Y., Liu, R., Xiong, B., Feng, A., Xu, J., Shi, Y. (2025). "IDU: Incremental Dynamic Update of Existing 3D Virtual Environments with New Imagery Data." I/ITSEC 2025.
Liu, Z., Xu, J., Suen, WK., Chen, M., Zou, Z., Shi, Y. (2025). "Egosafe: An Egocentric Camera-Based Method for Detecting Hazardous Objectives on Construction Sites." Automation in Construction.
Rahman, M.A., Xu, J., Liu, Z., Chen, M., Zhu, R., Liu, Y., Shi, Y., & Feng, A. (2024). "An Open Vocabulary Framework for Efficient 2D and 3D Visual Data Annotation in Indoor and Outdoor Built Environments." i3ce 2024.
Liu, Z., Xu, J., Suen, W.K., Chen, M., Zou, Z., Feng, A., & Shi, Y. (2024). "Detecting without Training: An Open-Vocabulary Object Detection Method for Identifying Hazardous Objects on Construction Sites." i3ce 2024.
Chen, M., Lal, D., Yu, Z., Xu, J., Feng, A., You, S., NURUNNABI, A. Shi, Y. (2024). "Large-Scale 3D Terrain Reconstruction Using 3D Gaussian Splatting for Visualization and Simulation." ISPRS.
Xu, J., Chen, M., Feng, A., Yu, Z., Shi, Y. (2024). "Open-Vocabulary High-Resolution 3D (OVHR3D) Data Segmentation and Annotation Framework." I/ITSEC 2024.
More publications coming soon...

Projects

LowDiff

In this work, we propose LowDiff, a novel and efficient diffusion framework based on a cascaded approach by generating increasingly higher resolution outputs. Besides, LowDiff employs a unified model to progressively refine images from low resolution to the desired resolution. With the proposed architecture design and generation techniques, we achieve comparable or even superior performance with much fewer high-resolution sampling steps. LowDiff is applicable to diffusion models in both pixel space and latent space.

Quantization in Robotics

Coming soon

News

December 7th - 10th 2025: Presented "GenVision: Enhancing Construction Safety Monitoring with Synthetic Image Generation" at WSC 2025.
August 2025: Obtained the 2025 ASCE Best Data Award.
April 24th 2025: Presented an IEEE-invited talk "Multiscale Conditional Diffusion on Image Generation" in a CS-themed seminar held by Colorado School of Mines.
August 2024: Started the Ph.D. program in Robotics under the supervision of Dr. Yangming Shi at the Colorado School of Mines.
July 28th - 31st 2024: Presented "An Open-vocabulary Framework for Efficient 2D-3D Visual Data Annotation in Indoor and Outdoor Built Environment" at i3ce 2024.
May 2024: Obtained a master's degree in Computer Science from the University of Southern California.
February 11th - 13th 2024: Presented "A Hybrid 2D-3D Zero-shot Framework for Photogrammetric Data Segmentation" at Geo Week 2024.
November 27th - December 1st 2023: Presented "USC-ICT Semantic Terrain Points Labeling System" at I/ITSEC 2023.
May 2023: Started as a student research intern at USC-ICT within the Geospatial Terrain Research group under the supervision of Dr. Meida Chen.
August 2022: Started the Master program in Computer Science at the University of Southern California.
More updates coming soon...