Xingjian Zhen
Research Scientist at Meta
Seattle, Washington, United States
Summary
👤
Senior🎓
Top SchoolXingjian Zhen is a research scientist with a PhD in computer science and nine years of experience focusing on algorithms for structured data and their applications in medical imaging and multi-modal problems. He specializes in leveraging non-Euclidean structures—like covariance matrices and graphs constrained as SPD—to build more robust, noise-resistant models that can detect subtle changes in medical data and improve tasks such as image-text VQA. His work blends theory and practice, from publishing explainable TextVQA models and assembling the TextVQA-X dataset to developing CPR-GCN and 3D CNN+BiLSTM pipelines for coronary artery labeling. Now at Meta after research roles at the Allen Institute and internships at AWS, Amazon, and Alibaba, he brings a proven track record of improving accuracy and interpretability in real-world systems. An understated strength is his focus on structure-aware noise augmentation and multimodal explanations that make high-level clinical signals actionable.
9 years of coding experience
2 years of employment as a software developer
Doctor of Philosophy - PhD Computer Science, Doctor of Philosophy - PhD Computer Science at University of Wisconsin-MadisonElectrical and Electronics Engineering, Electrical and Electronics Engineering at Tsinghua University
Chinese, English
Github Skills (65)
correlation10
depth-estimation10
variational-autoencoder10
autoencoder9
single-cell-analysis9
robust9
hierarchical9
gamma9
tsne9
partial9
recurrent9
information-theory9
graph-convolutional-networks8
deep-learning8
transcriptomics8
Programming languages (4)
Github contributions (5)
zhenxingjian/CV_Xingjian
Jul 2019 - Oct 2022
Contributions:58 commits, 57 pushes, 3 branches in 3 years 3 months
zhenxingjian/DCNN
Aug 2019 - May 2021
This is the published codes for Dilated Convolutional Neural Networks for Sequential Manifold-valued Data ICCV 2019
Contributions:10 commits, 9 pushes, 1 branch in 1 year 9 months
pytorchiccviccv-2019deep-learningconvolutional
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.