Yinda Xu
Research Assitant at 上海交通大学
Shanghai, China
Summary
👤
Senior🎓
Top SchoolYinda Xu is a PhD student and research assistant in Computer Science at Shanghai Jiao Tong University specializing in Robot Learning and Embodied AI, with eight years of experience across academia and industry. He has applied deep reinforcement learning, trajectory optimization, and reachability analysis to real-world autonomy problems during roles at DeepRoute.ai, Momenta and research internships at Megvii and Zhipu.ai. His work spans manipulation, motion planning, multi-agent decision-making and visual tracking, and he contributed one-shot detection integration to Megvii’s widely used video_analyst repository. Trained originally in electrical engineering at Zhejiang University, he combines strong systems-background with hands-on research in laboratory automation and humanoid locomotion. Known for bridging research and production, he is currently exploring reasoning abilities of vision-language-action (VLA) manipulation models.
8 years of coding experience
3 years of employment as a software developer
Master's degree Electrical Engineering, Master's degree Electrical Engineering at Zhejiang UniversityEngineer’s Degree Ingénieur généraliste, Engineer’s Degree Ingénieur généraliste at Centrale MéditerranéeHigh School Diploma Science, High School Diploma Science at Hangzhou High SchoolDoctor's Degree Computer Science, Doctor's Degree Computer Science at Shanghai Jiao Tong University
Github Skills (6)
object-tracking10
computer-vision10
pytorch10
python10
video-understanding10
tensorflow7
Programming languages (10)
Github contributions (5)
megvii-research/video_analyst
Dec 2019 - Sep 2020
A series of basic algorithms that are useful for video understanding, including Single Object Tracking (SOT), Video Object Segmentation (VOS) and so on.
Role in this project:
Back-end Developer
Back-end DeveloperContributions:230 commits, 44 PRs, 31 pushes in 8 months
Contributions summary:Yinda contributed to the implementation of a one-shot detection demo for the video_analyst repository, resolving conflicts and adding related code. They added and modified the `SiamFCppOneShotDetector` class within the `videoanalyst/pipeline/tracker/tracker_impl` directory. The contributions focused on integrating one-shot detection functionality, enhancing the repository's capabilities for object tracking and video understanding.
understandingsotobject-detectioncomputer-visiontracking
MARMOTatZJU/video_analyst
Feb 2020 - Dec 2020
A series of basic algorithms which is useful for video understanding, including Single Object Tracking (SOT) , Video Object Segmentation (VOS),
Contributions:182 pushes, 24 branches in 10 months
understandingsotobject-detectioncomputer-visiontracking
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.