Ziyue Feng
Multimodal Generative MLE
California, United States
Summary
👤
Senior🎓
Top SchoolZiyue Feng is a Machine Learning Engineer and PhD-trained 3D computer vision researcher with 8 years of experience building spatiotemporal and world models for autonomous systems and reconstruction. Currently a Multimodal Generative MLE at Apple, Ziyue brings a track record of translating cutting-edge research into practical systems—from state-of-the-art self-supervised monocular depth models (ECCV 2022) and LiDAR-fusion work (CoRL 2021) to contributions on Project Starline and 3D Active Neural SLAM during industry research internships. Comfortable across computer vision, autonomous driving, and generative modeling, they have repeatedly improved robustness in dynamic scenes and low-sensor regimes (e.g., halving depth error with a 4-beam LiDAR). Based in California, Ziyue combines rigorous academic foundations with production-focused engineering, often bridging novel geometric insights with scalable implementations.
8 years of coding experience
4 years of employment as a software developer
Doctor of Philosophy - PhD, 3D Computer Vision, Doctor of Philosophy - PhD, 3D Computer Vision at Clemson UniversityBachelor's degree, Computer Science, Bachelor's degree, Computer Science at Xi'an Jiaotong University
Github Skills (96)
depth-estimation10
convolutional-neural-networks10
sensor-fusion10
pointnet10
raycasting10
kitti10
lidar10
depth10
visual-odometry9
abaqus9
kitti-dataset9
self-supervised-learning9
backbone9
stereo9
mvs9
Programming languages (5)
Github contributions (5)
fengziyue/RRT-Parking
Dec 2017 - Nov 2022
Contributions:13 commits, 4 pushes, 3 comments in 4 years 11 months
fengziyue/ziyue-s-homepage
Jun 2020 - Oct 2022
Contributions:129 commits, 172 pushes, 7 branches in 2 years 3 months
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.