Ming-Yu Liu 劉洺堉
United States
Summary
🤩
RockstarMing-yu Liu is Vice President of Research at NVIDIA, leading company-wide initiatives in Generative AI and physical-simulation AI. He advanced through multiple senior research roles at NVIDIA after prior research and engineering stints at MERL and Intel, bringing an 11-year industry research track record to bear on strategic programs. An active contributor to NVLabs projects (SPADE, MUNIT, FUNIT, FastPhotoStyle), he works across the stack—from PyTorch model internals and CUDA-accelerated components to demo UIs like a petswap front end—reflecting a rare blend of deep model expertise and product-facing engineering. He holds a PhD in Electrical Engineering from the University of Maryland and is known for attending to practical deployment details such as licensing, demos, and containerized dependencies that help move research into use.
11 years of coding experience
Github Skills (21)
pytorch10
javascript10
python10
dcgan10
image-processing10
machine-learning10
image-translation10
cgan10
style-transfer10
deep-learning10
javascripts10
html10
computer-vision10
user-interface9
userinterface9
Programming languages (3)
Github contributions (5)
NVlabs/FUNIT
May 2019 - Apr 2021
Translate images to unseen domains in the test time with few example images.
Role in this project:
Full-stack Developer
Full-stack DeveloperContributions:23 commits, 20 pushes, 1 branch in 1 year 11 months
Contributions summary:Ming-Yu contributed significantly to the project's front-end, adding and modifying the user interface. They added a demo page (`petswap.html`) and the accompanying javascript code (`petswap.js`) for a pet-swapping feature. The commits also show updates to the main project documentation (`index.html`), including links to the paper, code, and demo, indicating a focus on user experience and project presentation. Furthermore, they addressed bugs within the javascript and HTML files to improve functionality.
unseenimage-synthesiscomputer-visiontranslatedomains
NVlabs/SPADE
Apr 2019 - Sep 2021
Semantic Image Synthesis with SPADE
Role in this project:ML Engineer
ML EngineerContributions:18 commits, 14 pushes, 19 comments in 2 years 5 months
Contributions summary:Ming-Yu appears to be focused on modifications related to the non-commercial release of the project. The commits primarily involve changes to the `pix2pix_model.py` file, indicating a deep understanding of the core model architecture. Additional commits update the demo.html file, likely to redirect users, which may reflect efforts related to licensing or usage restrictions.
spadeimage-synthesisdeep-learningsynthesissemantic-image-synthesis
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.