Kevin Chen

Spatial AI & On-Device ML Systems Engineer

I build perception systems.

My work spans real-time SLAM/VIO, 3D mapping, and on-device multimodal ML.

8+ years
production computer vision
CVPR 2025
active 3D mapping
3 papers
vision and robotics
5 patents
spatial AI systems

Selected systems

All projects
On-Device VLM Perception
Current exploration Present

On-Device VLM Perception

VLM-based perception for health-oriented experiences, visual composition, and multimodal interaction.

ActiveGAMER
CVPR 2025 2025

ActiveGAMER

CVPR 2025 research on active 3D Gaussian mapping and autonomous exploration.

selected publications

  1. ActiveGAMER: Active GAussian Mapping through Efficient Rendering
    Liyan Chen, Huangying Zhan, Kevin Chen, Xiangyu Xu, Qingan Yan, Changjiang Cai, and Yi Xu
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Jun 2025
  2. Stereo-NEC: Enhancing Stereo Visual-Inertial SLAM Initialization with Normal Epipolar Constraints
    Weihan Wang, Chieh Chou, Ganesh Sevagamoorthy, Kevin Chen, Zheng Chen, Ziyue Feng, Youjie Xia, Feiyang Cai, Yi Xu, and Philippos Mordohai
    In 2024 IEEE International Conference on Robotics and Automation, 2024
  3. The World Is Changing: Finding Changes on the Street
    Kuan-Ting Chen, Fu-En Wang, Juan-Ting Lin, Fu-Hsiang Chan, and Min Sun
    In Computer Vision – ACCV 2016 Workshops, 2016