I am a final-year Ph.D. candidate in CityU (SDS), supervised by Prof. James Jianqiao Yu, Prof. Xiangyu Zhao, and Prof. Xuetao Wei. Previously, I received my B.S. degree from Shandong University in 2019 and my M.Phil. degree from the Southern University of Science and Technology in 2022.
📢I am on the job market! I am actively seeking Postdoc / Research Scientist positions starting from Fall 2026. Feel free to reach out via email if you have any opportunities!
My research interests lie at the intersection of artificial intelligence, smart cities, and data mining. I focus on developing foundation models for spatiotemporal data, advancing generative AI for urban systems, and applying large language models to real-world intelligent applications. My work spans from theoretical model design to practical deployment in urban mobility, recommendation systems, and intelligent decision-making.
Research Focus
The themes that guide my current work and collaborations.
Generative AI for Smart Cities
Diffusion models and controllable generation for human mobility analysis and simulation.
DiffTraj · ControlTraj · SynMob
Foundation Models for Spatial Data
Building universal representations for urban mobility and geospatial understanding.
UniTraj · OmniTraj · WorldTrace
LLMs & Applications
Parameter-efficient fine-tuning, semantic enhancement, and intelligent decision-making.
@inproceedings{zhu2026boosting,title={Boosting Fine-Grained Urban Flow Inference via Lightweight Architecture and Focalized Optimization},author={Zhu, Yuanshao and Zhao, Xiangyu and Zhang, Zijian and Wei, Xuetao and Yu, James Jianqiao},booktitle={Proceedings of the AAAI conference on artificial intelligence},volume={40},year={2026},}
NeurIPS
UniTraj: Learning a Universal Trajectory Foundation Model from Billion-Scale Worldwide Traces
Yuanshao Zhu, James Jianqiao Yu, Xiangyu Zhao, Xun Zhou, Liang Han, Xuetao Wei, and Yuxuan Liang
In Proceedings of the 39th Annual Conference on Neural Information Processing Systems, 2025
@inproceedings{zhu2025unitraj,title={UniTraj: Learning a Universal Trajectory Foundation Model from Billion-Scale Worldwide Traces},author={Zhu, Yuanshao and Yu, James Jianqiao and Zhao, Xiangyu and Zhou, Xun and Han, Liang and Wei, Xuetao and Liang, Yuxuan},booktitle={Proceedings of the 39th Annual Conference on Neural Information Processing Systems},year={2025},}
KDD
Learning Generalized and Flexible Trajectory Models from Omni-Semantic Supervision
Yuanshao Zhu, James Jianqiao Yu, Xiangyu Zhao, Xiao Han, Qidong Liu, Xuetao Wei, and Yuxuan Liang
In Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2025
@inproceedings{zhu2025learning,title={Learning Generalized and Flexible Trajectory Models from Omni-Semantic Supervision},author={Zhu, Yuanshao and Yu, James Jianqiao and Zhao, Xiangyu and Han, Xiao and Liu, Qidong and Wei, Xuetao and Liang, Yuxuan},booktitle={Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining},year={2025},}
KDD
ControlTraj: Controllable Trajectory Generation with Topology-Constrained Diffusion Model
Yuanshao Zhu, James Jianqiao Yu, Xiangyu Zhao, Qidong Liu, Yongchao Ye, Wei Chen, Zijian Zhang, Xuetao Wei, and Yuxuan Liang
In Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2024
@inproceedings{zhu2024controltraj,title={ControlTraj: Controllable Trajectory Generation with Topology-Constrained Diffusion Model},author={Zhu, Yuanshao and Yu, James Jianqiao and Zhao, Xiangyu and Liu, Qidong and Ye, Yongchao and Chen, Wei and Zhang, Zijian and Wei, Xuetao and Liang, Yuxuan},booktitle={Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining},year={2024},}
NeurIPS
DiffTraj: Generating GPS Trajectory with Diffusion Probabilistic Model
Yuanshao Zhu, Yongchao Ye, Shiyao Zhang, Xiangyu Zhao, and James J.Q. Yu
In Proceedings of the 37th Annual Conference on Neural Information Processing Systems, 2023
@inproceedings{zhu2023difftraj,title={DiffTraj: Generating GPS Trajectory with Diffusion Probabilistic Model},author={Zhu, Yuanshao and Ye, Yongchao and Zhang, Shiyao and Zhao, Xiangyu and Yu, James J.Q.},booktitle={Proceedings of the 37th Annual Conference on Neural Information Processing Systems},year={2023},}
@inproceedings{zhu2023synmob,title={SynMob: Creating High-Fidelity Synthetic GPS Trajectory Dataset for Urban Mobility Analysis},author={Zhu', Yuanshao and Ye', Yongchao and Wu, Ying and Zhao, Xiangyu and Yu, James J.Q.},booktitle={Proceedings of the 37th Annual Conference on Neural Information Processing Systems},year={2023},}
