Hi!

I am Xiang Zhang, a second year CS Ph.D. student at UCSD. My advisor is Prof Zhuowen Tu. Previously, I obtained my bachelor's degree in Computer Science and Technology at Tsinghua University in 2021.

My current research interest spans multi-modal learning, where I am particularly interested in leveraging pre-trained large-scale vision-language models to solve downstream tasks, such as panoptic reconstruction.

Latest publications

Uni-3D: A Universal Model for Panoptic 3D Scene Reconstruction
Xiang Zhang*, Zeyuan Chen*, Fangyin Wei, Zhuowen Tu

ICCV 2023

Text Spotting Transformers [pdf] [code]
Xiang Zhang, Yongwen Su, Subarna Tripathi, Zhuowen Tu

CVPR 2022

Pose Recognition with Cascade Transformers [pdf] [code]
Ke Li*, Shijie Wang*, Xiang Zhang*, Yifan Xu, Weijian Xu, and Zhuowen Tu

CVPR 2021