Currently, I am a Senior Researcher at the Computer Vision Lab in Huawei Noah’s Ark Lab. I am leading a research team in Shanghai. We are focusing on industrial research in deep learning and high-level recognition machine learning technics in computer vision in Huawei.

Recently, my research interest includes:

High-level Recognition Models including 2D/3D Object Detection, Segmentation, Lane detection in Autonomous Driving.
Multi-modality Learning, such as image-text pretrained models, large-scale pretrained models, Lidar/Camera perception models.
Automatic Machine Learning (AutoML), specially on NAS and HPO.