Jiajun Wu

Email: jiajunwu [at] cs (dot) stanford (dot) edu

Google Scholar / DBLP / Stanford Profiles

Research Communities

I am an Assistant Professor of Computer Science and, by courtesy, of Psychology at Stanford University. Before joining Stanford, I was a Visiting Faculty Researcher at Google Research, working with Noah Snavely. I finished my PhD at MIT, advised by Bill Freeman and Josh Tenenbaum, and my undergraduate degrees at Tsinghua University, working with Zhuowen Tu.

Research

My group studies physical scene understanding---building machines that see, reason about, and interact with the physical world. Besides learning algorithms, what are the levels of abstraction needed by AI systems in their representations, and where do they come from? Our research aims to answer these fundamental questions, drawing inspiration from nature, i.e., the physical world itself, and from human cognition. Representative projects include Galileo, MarrNet, 4D Roses, the Neuro-Symbolic Concept Learner, and the Scene Language.

In addition to developing the representations themselves, we simultaneously explore their applications in various domains:

multi-modal perception from visual, acoustic, and tactile signals, as in ObjectFolder and RealImpact;
visual generation of the 4D, physical world, as in 3D-GAN, pi-GAN, Point-Voxel Diffusion, SDEdit, and WonderWorld;
visual reasoning via physical concept grounding, often in a neuro-symbolic way, as in NS-VQA, Shape Programs, CLEVRER, and LEFT;
robotics and embodied AI using the learned physical scene representations, as in RoboCook and BEHAVIOR.

Here is some information for prospective students and visitors.

Thank you for your interest in joining my group! Due to the large number of emails I receive, I cannot respond to every email individually. Please review the information below before contacting me. Thanks.

Current Stanford students and prospective visiting students: please fill out this form. For Stanford MS students and undergraduates, the minimum time commitment is 15 hours per week for six months. For visiting graduate students, the minimum length of a visit is six months.

Prospective postdocs: please email me directly with your CV.

Prospective graduate students: please apply through the system and list me as a potential advisor in your application. There is no need to contact me, unless you have a particular research question/idea that you would like to discuss further.

Group

Postdocs

Weiyu Liu
Mengdi Xu (with Fei-Fei Li)
Ruohan Zhang (with Fei-Fei Li and Silvio Savarese)

PhD Students

Samuel Clarke
Cristobal Eyzaguirre (with Juan Carlos Niebles)
Chen Geng
Michelle Guo (with Karen Liu)
Joy Hsu
Kyle Hsu (with Chelsea Finn)
Jiaman Li (with Karen Liu)
Zizhang Li
Kyle Sargent (with Fei-Fei Li)
Stephen Tian
Koven Yu
Yanjie Ze (with Karen Liu)
Yunzhi Zhang

Affiliates

Alumni

Stefan Stojanov (postdoc 2025, with Dan Yamins), Applied Scientist, Amazon
Elliott Wu (postdoc 2024), Assistant Professor, University of Cambridge
Manling Li (postdoc 2024), Assistant Professor, Northwestern University
Yunzhu Li (postdoc 2023, with Fei-Fei Li), Assistant Professor, Columbia University
Ruohan Gao (postdoc 2023, with Fei-Fei Li and Silvio Savarese), Assistant Professor, University of Maryland, College Park
Sumith Kulal (PhD 2023, with Alex Aiken), Co-Founder, Black Forest Labs
Michael Lingelbach (2023, with Fei-Fei Li), CEO, Hedra
Huazhe Xu (postdoc 2022), Assistant Professor, Tsinghua University