Tai Wang
Research Scientist at 上海人工智能实验室
Xuhui District, Shanghai, China
Summary
🤩
Rockstar🎓
Top SchoolTai Wang is a research scientist at Shanghai AI Lab with eight years of experience building multi-modal, ego-centric foundation models for 3D perception and embodied intelligence. His work spans academia and industry—PhD-trained in information engineering with prior roles at SenseTime, Alibaba, and CUHK—focused on efficient LiDAR annotation, real-time 3D detection, and robot perception. He contributes to high-impact open-source projects such as OpenMMLab’s mmdetection3d, where he implemented dataset support, test-time augmentation, and critical bug fixes to improve 3D detection pipelines. Combining systems-oriented engineering with applied research, he aims to enable general physical intelligence from first-person sensors. Colleagues note his practical knack for turning complex 3D research ideas into production-ready tools and reproducible evaluation code.
8 years of coding experience
3 years of employment as a software developer
Bachelor of Engineering - BE, Information Engineering, 92.1/100, Bachelor of Engineering - BE, Information Engineering, 92.1/100 at 浙江大学Doctor of Philosophy - PhD, Information Engineering, Doctor of Philosophy - PhD, Information Engineering at 香港中文大学
Github Skills (9)
object-detection10
pytorch10
3d-object-detection10
deep-learning10
data-integration9
data-set9
datasets9
computer-vision9
configuration-management8
Programming languages (2)
Github contributions (5)
open-mmlab/mmdetection3d
Jul 2020 - Jan 2023
OpenMMLab's next-generation platform for general 3D object detection.
Role in this project:
Back-end Developer & ML Engineer
Back-end Developer & ML EngineerContributions:3 releases, 1456 reviews, 127 commits in 2 years 6 months
Contributions summary:Tai primarily worked on improving the performance and functionality of 3D object detection, specifically focusing on test-time augmentation and adding support for a new dataset (Lyft). They addressed a bug related to random flipping and implemented APIs to support a new dataset. The user also updated several configuration files and implemented the code required to support features related to evaluating performance.
pytorchnext-generationkitti-datasetdeep-learningobject-detection
Tai-Wang/mmdetection3d
Jul 2020 - Dec 2022
OpenMMLab's next-generation platform for general 3D object detection.
Contributions:10 PRs, 648 pushes, 165 branches in 2 years 5 months
pytorchnext-generationdeep-learningobject-detectioncomputer-vision
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.