

Make Geometry Matter for Spatial Reasoning
ECCV 2026Award Candidate · Oral
Vision-language models · Spatial reasoning
I am a second-year Ph.D. student in the Department of Electrical and Computer Engineering at the National University of Singapore, advised by Prof. Xinchao Wang. My current research interests include vision-language models, video generation, and world models.
Previously, I received my M.S. degree from Wuhan University, where I was advised by Prof. Jiayi Ma and worked on image matching.
suhzhang001@gmail.com
* Equal contribution


ECCV 2026Award Candidate · Oral
Vision-language models · Spatial reasoning






CVPR 2024
Image matching


TPAMI 2024 · AAAI 2023AAAI Oral
Image matching
Ph.D. student in Electrical and Computer Engineering · xML Lab
Advisor: Prof. Xinchao Wang
M.S. in Information and Communication Engineering
Multi-Spectral Vision Processing Lab · Advisor: Prof. Jiayi Ma
B.E. in Electronic Information Engineering
Electronic Information School
Xiamen, China
Worked on monocular 3D object detection and pose estimation in indoor scenes, using an end-to-end network with weak shape supervision.
CVPR / ECCV / NeurIPS / AAAI
TPAMI / IJCV / TCSVT / PR