Yuan Qing

Yuan Qing

My research interests lie in multi-modal learning and perception, with an emphasis on developing unified visual and sensory representations that enable intelligent systems to understand and interact with the physical world. I am particularly focused on advancing the training efficiency, interpretability, and systematic evaluation of large-scale multi-modal foundation models, toward building generalizable and robust perception systems for real-world applications.

Bio

I am an incoming CS PhD student at Rutgers University. I was a visiting student at Boston University, working with Prof. Boqing Gong. I received my M.S. in Electrical Engineering at Columbia University, where I worked with Dr. Jingxi Xu. Previously, I obtained my B.Eng. in Electronic Information Engineering at UESTC, advised by Prof. Lixin Duan.

Publications

* Equal contribution

Moiré method illustration
Moiré Video Authentication: A Physical Signature Against AI Video Generation
Yuan Qing*, Kunyu Zheng*, Lingxiao Li*, Boqing Gong, Chang Xiao
arXiv 2026
arXiv   Project Page
HCA paper cover
The LLM Bottleneck: Why Open-Source Vision LLMs Struggle with Hierarchical Visual Recognition
Yuwen Tan*, Yuan Qing*, Boqing Gong
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026
arXiv   Project Page
PRCV paper cover
Multi-modal Instance Refinement for Cross-domain Action Recognition
Yuan Qing, Naixing Wu, Shaohua Wan, Lixin Duan
Chinese Conference on Pattern Recognition and Computer Vision (PRCV), 2023
arXiv

Projects

Learning Tactile Policies for Complex Manipulation Tasks in Simulation

Tactile Simulation

A demo tactile simulator tailored for DIGIT fingers in IsaacLab.

AIRPOSE Dataset for Syn2Real 6D Pose Estimation

AIRPOSE Dataset

See this for details.

Selected Honors