AI Research · HKUST(GZ)
Modeling a world
that keeps moving.
I build generative models that maintain world state and follow physical dynamics, with applications in autonomous driving and embodied intelligence.
I’m a Ph.D. student in Artificial Intelligence at HKUST(GZ), advised by Prof. Yingcong Chen. Previously, I received my bachelor’s and master’s degrees from Xiamen University, advised by Prof. Rongrong Ji.
01 / Research
Persistent memory.
Physically consistent motion.
Teaching video generators to remember.
A causal video generator with dynamic memory: objects and events keep evolving through camera motion, occlusion, and changes in visibility.
The view disappears.
The world keeps moving.
Eight examples, two chapters. Complete sequences at original speed: visible → hidden → evolved.
Explore all examples ↗Controllable motion, consistent physics.
A decoupled framework for robust video generation that separates camera and object control, with applications in driving, rigid-body dynamics, and robotic grasping.
Same scene. Different controls.
Motion follows your intent.
Compare left cut-in + braking with right cut-in. Control inputs stay visible above synchronized results.
Explore all controls ↗02 / Experience
Research internships
across industry.
Research Intern · Research Team
Developed ReMind to elicit dynamic memory in video diffusion transformers and enable coherent out-of-sight state evolution.
Research Intern · Noah’s Ark Lab
Developed Occ-LLM for occupancy forecasting, planning, and scene question answering. Built generative world models for autonomous driving.
Research Intern · Foundation Model Group
Optimized large diffusion models for image synthesis and explored fine-tuning and prompt-tuning for perceptual image super-resolution.
03 / Publications
My name is highlighted. * denotes equal contribution.
Tianshuo Xu, Y. Xie, D. Meng, et al.
Tianshuo Xu, Z. Chen, L. Wu, H. Lu, Y. Chen
Z. Chen, Tianshuo Xu*, L. Wu, et al.
Tianshuo Xu, K. Wang, Z. Chen, et al.
H. Lu, Tianshuo Xu*, W. Zheng, et al.
Tianshuo Xu, H. Lu, X. Yan, et al.
Z. Chen, Tianshuo Xu*, W. Ge, et al.
Tianshuo Xu, L. Li, P. Mi, et al.
8 publications shown
04 / Contact
World models, generative video, and physical intelligence.