I am a senior researcher in computer vision and multimodal learning at Huawei Hisilicon. My work focuses on translating cutting-edge research into commercial AI solutions. I have developed perceptual visual quality enhancement models currently deployed on cloud media services and low-power multimodal perception models that run in agents for smartphones. Before joining Huawei, I earned a dual PhD in Computer Science from City University of Hong Kong and Dalian University of Technology in 2023. My research has been published at top-tier venues including CVPR, AAAI, IJCV, TIP, TDSC, and BMVC, and I received the Best Student Paper Runner-Up Award at BMVC 2020.

Computer Vision Deep Learning Multi-Modality Learning GUI Agent
Alex Warren, Ke Xu, Xin Tian, Gary Tam, Benjamin Wah, Rynson Lau
AAAI, 2026
Xin Tian, Ke Xu, Rynson Lau
CVPR, 2024
Zeming Yao, Hangtao Zhang, Yicheng Guo, Xin Tian, Wei Peng, Yi Zou, Leo Yu Zhang, Chao Chen
IEEE Transactions on Dependable and Secure Computing (TDSC), 2024
Xin Tian, Ke Xu, Xin Yang, Lin Du, Baocai Yin, Rynson Lau
CVPR, 2022
Xin Tian, Ke Xu, Xin Yang, Baocai Yin, Rynson Lau
International Journal of Computer Vision (IJCV), 2022
Ke Xu, Xin Tian, Xin Yang, Baocai Yin, Rynson Lau
IEEE Transactions on Image Processing (TIP), 2021
Weakly-supervised Salient Instance Detection Oral Best Student Paper Runner-Up
Xin Tian, Ke Xu, Xin Yang, Baocai Yin, Rynson Lau
BMVC, 2020