Yihang Tao | 陶祎航
PhD Student
City University of Hong Kong
Research Interests
- World Model
- Spatial Intelligence
- Autonomous Driving
- Computer Vision
About Me
I am currently pursuing my PhD degree in the Department of Computer Science at City University of Hong Kong, advised by Prof. Yuguang "Michael" Fang. Before that, I received my B.S. degree from the School of Information Science and Engineering, Southeast University, Nanjing, China, in 2021, and my M.S. degree from the School of Computer Science, Shanghai Jiao Tong University, Shanghai, China, in 2024. My research lies at the intersection of World Model, Spatial Intelligence, Computer Vision, and Autonomous Driving, with a particular interest in building learning-based systems that can perceive, reconstruct, predict, and reason about dynamic 3D environments.
I am actively seeking collaborators of like-minded interests. If you are interested in my work, please feel free to contact me via email: yihang.tommy@my.cityu.edu.hk.
🚀 Research Thrust
"My long-term goal is to build a World Model for Spatial Intelligence: a unified representation that enables intelligent agents to perceive 3D scenes, reason about dynamics, and anticipate how the world may evolve. I am particularly interested in grounding this capability in Computer Vision, Generative Models, and Autonomous Driving."
Towards this goal, my research studies how to learn scalable World Models from visual observations, sparse sensor streams, and multi-agent interactions. In particular, I focus on 3D Vision, Generative Models, and Collaborative Perception for Autonomous Driving, organized into two closely connected thrusts:
Collaborative 3D Vision for Scalable World Modeling
This thrust studies how to scale the spatial coverage and reliability of a World Model beyond a single ego view. By leveraging Collaborative Perception across agents, I aim to recover occluded structure, fuse complementary observations, and maintain robust 3D understanding under adversarial, bandwidth-constrained, and real-world driving conditions. This direction is closely connected to my work on multi-agent perception, robustness, and secure 3D vision for Autonomous Driving.
Generative 3D Vision for Predictive World Modeling
This thrust studies how to enrich the temporal and generative capacity of a World Model. By combining Generative Models, 3D Gaussian Splatting, and Multimodal Foundation Models, I aim to reason about dynamic visual geometric from sparse or unstructured observations and predict plausible future states of the environment. This direction is closely tied to my recent work on scene generation, dynamic reconstruction, and predictive modeling for Autonomous Driving.
🔥 News
View All📄 Publications
(* means equal contribution)
🏆 Honors & Awards
View All💼 Academic Service
Conference Reviewer
Program Committee Member
CVPR, ECCV, ICML, NeurIPS, ICLR, ACM MM, IROS, ICASSP, IJCNN
Journal Reviewer
Peer Review
IEEE TMC, IEEE TITS, IEEE TCE, Pattern Recognition, Neural Networks, EAAI, IEEE JBHI, IEEE LNET
Session Chair
IEEE GLOBECOM 2023
MWN Track, Semantic Communications Session
Teaching Assistant
City University of Hong Kong
🎓 Education
PhD @ City University of Hong Kong
Sep. 2024 - Now
Department of Computer Science
Supervisor: Prof. Yuguang "Michael" Fang
MEng @ Shanghai Jiao Tong University
Sep. 2021 - Apr. 2024
School of Computer Science
BEng @ Southeast University
Sep. 2017 - Jul. 2021
School of Information Engineering
📍 Contact
Office Address
83 Tat Chee Avenue Kowloon, Hong Kong