Xiaotong Liu | XMotors.AI

About Me

I am currently a Senior Computer Vision Engineer at XMotors.AI, where I conduct research and develop vision-language models (VLMs) and large language models (LLMs) for self-driving systems and intelligent cabins. Previously, I was a Ph.D. student at the School of Engineering and Applied Science at George Washington University, where I conducted research in the field of computer vision under the guidance of Professor Robert B. Pless. My work focused on providing visual explanations for deep learning models, particularly in the context of deep metric learning—an area with impactful applications such as face re-identification and image retrieval.

Currently, my research explores the application of vision-language models (VLMs) in autonomous driving. I focus on using VLMs and LLMs as decision-making agents to enhance vehicle safety and provide a more comfortable and intelligent in-cabin experience for every passenger.

Publications

Hard negative examples are hard, but useful
H.Xuan, A.Stylianou, X.Liu, & R. Pless
2020 European Conference on Computer Vision, ECCV 2020.
[PDF]
2-map: Aligned visualizations for comparison of high-dimensional point sets
X.Liu, Z.Zhang, H.Xuan, R.Leontie, A.Stylianou, & R. Pless
2020 IEEE Winter Conference on Applications of Computer Vision, WACV 2020.
[PDF]
Visualizing how embeddings generalize
X.Liu, H.Xuan, Z.Zhang, A.Stylianou, & R. Pless
Understanding and Improving Generalization in Deep Learning Workshop,
36th International Conference on Machine Learning, ICML 2019.
[PDF]
Visualizing Data Driven Phenotypes
Z.Zhang, X.Liu, H.Xuan, A.Stylianou, & R. Pless
Computer Vision Problems in Plant Phenotyping Workshop at
Conference on Computer Vision and Pattern Recognition, CVPPP@CVPR 2019.
[PDF]
Subspace Based Visualization for Embedding Network.
X.Liu, A.Stylianou, Z.Zhang, & R. Pless
Explainable AI for Computer Vision Workshop at Conference on Computer Vision and Pattern Recognition, XAI4CV@CVPR 2022.
[PDF]