Hi there, this is Xingrui! ๐
I am a PhD student in the Computer Science Department at Johns Hopkins University, advised by Prof. Alan Yuille. I am currently also interning with the GenAI group at AMD.
Before JHU, I obtained my Masterโs degree from the University of Southern California, where I worked closely with Prof. Laurent Itti. Prior to USC, I received my B.S. in Statistics from Renmin University of China, where I was supervised by Prof. Hanfang Yang. I also spent time in the AI lab at the Samsung R&D Institute, supervised by Dr. Yang Liu.
My research focuses on 3D scene understanding and spatial reasoning, especially estimating object pose and developing vision-language models for 3D/4D reasoning. I also explore generative models for video and 3D object synthesis.
โ๏ธ: xwang378@jhu.edu
๐ฃ News
- Invited talk at BEAM Workshop at CVPR 2025 (slides). (Jun 2025)
- Spatial457 accepted at CVPR 2025 as a highlight paper! (Feb 2025)
- One paper accepted at ICLR 2025. (Jan 2025)
- Introduced NS-4DPhysics and DynSuperCLEVR: a 4D neural symbolic model and benchmark for dynamic spatial reasoning. (May 2024)
Show older news
- One paper accepted by NeurIPS 2023. (Sep 2023)
- Joined CCVL at JHU as a PhD student. (Aug 2023)
- SuperCLEVR selected as a highlight in CVPR 2023. (Mar 2023)
- One paper accepted at CVPR 2023. (Feb 2023)
- One paper accepted at ECCV 2022
Selected Publications
(Full list available on Google Scholar)





Service
- I am invited as a reviewer for CVPR, ICCV, NeurIPS, ICLR, WACV.
- Co-host Advml Workshop at CVPR 2025.