Bio
I am an assistant professor in the School of Data Science at CUHK-Shenzhen. I did my PhD in computer science at Mila and Université de Montréal with Liam Paull and Yoshua Bengio. During my PhD study, I visited at Max Planck Institute for Intelligent Systems, and worked with Michael J. Black and Bernhard Schölkopf. I received my M.S. and B.S. degrees in computer science with a minor in economics from Georgia Tech.
Students interested in Spring '26 / Fall '27 admission are welcome to contact me (and potentially collaborate as an RA) in advance. We also welcome visiting students and RAs with strong background in either 3D generation or foundation models.
To apply for positions:
- If you are affiliated with CUHK-Shenzhen. Shoot me an email with your resume and experiences.
- If you are outside CUHK-Shenzhen. Please fill out the Google Form and then drop me an email if interested.
Due to the large volume of emails, I apologize that I am not able to reply to every email.
Research
I study representations and learning methods to develop models with a spatial, physical, and semantic understanding for re-creating and simulating our world. I draw on principles and theories from machine learning and related fields to discover simple and effective approaches that generalize well across diverse domains.
More specifically, my current focuses are:
- Post-training and adaptation methods for foundation models. Designing 1) efficient and effective post-training methods, as in DrPO, VGG-Flow, PGD, Nabla-GFlowNet, and 2) post-training/guidance signals to improve domain-specific models, as in EVA (world action model), ASAP (text-to-image), Nabla-R2D3 (3D generation),
- Agentic 3D reasoning and generation. Building agentic workflow and harness so that agents are capable of understanding and creating physiclally-sound, functional and manufacturable 3D assets and scenes, as in BesiegeField, ChatGarment, SGP-Bench,
- 3D vision for spatial and physical intelligence. Building efficient methods that generate 3D assets (meshes, CAD models) and world models that better incoporate 3D and physical priors, as in PAct, MeshDiffusion, EVA,
What's more? I am also actively exploring the following topics:
- Agentic reasoning
- Generative models / probalistic methods
- VLA, WAM, etc.
Students
PhD Students
- Wenqian Zhang
- Zhou Jiang
MPhil Students
- Jinming Ren
Visiting Students / RAs
- Yaocheng Guo, master student @ CUHK-Shenzhen
- Xiangwei Shen, master student @ CUHK-Shenzhen
- Zihao Zhou, undergrad student @ Xi'an Jiaotong University
- Zhuoran Xia, undergrad student @ CUHK-Shenzhen
- Jinlong Yang, undergrad student @ Sichuan University
Alumni
- Qingming Liu, MPhil @ CUHK-Shenzhen -> PhD student @ HKUST
- Zhou Jiang, undergrad @ SCUT -> PhD student @ CUHK-Shenzhen
- Yuping Zheng, undergrad @ CUHK-Shenzhen -> PhD student @ University of Virginia
- Bao Li, master student @ Chinese Academy of Sciences, w/ Yuliang Xiu -> PhD student @ Chinese Academy of Sciences