Rinon Gal
Research Intern at NVIDIA
Israel
Summary
🤩
Rockstar🎓
Top SchoolRinon Gal is a Computer Science PhD candidate at Tel Aviv University specializing in generative models for 2D and 3D data with an emphasis on reducing supervision, currently interning at NVIDIA Research. With a decade of experience spanning academic research, industry R&D, and hands-on ML engineering, he has contributed practical improvements to popular projects like StyleGAN-NADA for Colab-driven domain adaptation and checkpointing. His background in physics (BSc Tel Aviv, MSc Weizmann) informs a quantitative, simulation-first approach to problems, from large-scale data interpolation to signal analysis. He combines rigorous theoretical research under advisors Daniel Cohen-Or and Amit Bermano with pragmatic tooling and reproducibility work, making models easier to train and apply. Notably, he bridges deep generative research and developer-friendly implementations that accelerate experimentation and deployment.
9 years of coding experience
5 years of employment as a software developer
Bachelor’s Degree, Physics, 97, Bachelor’s Degree, Physics, 97 at Tel Aviv UniversityMaster’s Degree, Physics, 93, Master’s Degree, Physics, 93 at Weizmann Institute of Science
English, Hebrew
Github Skills (11)
pytorch10
machine-learning10
jupyter-notebook10
stylegan10
python10
generative-adversarial-network10
adaptation10
google-colaboratory9
image-generation9
google-colab9
clip8
Programming languages (2)
Github contributions (5)
rinongal/StyleGAN-nada
Jun 2021 - Aug 2022
Role in this project:
ML Engineer
ML EngineerContributions:36 commits, 9 PRs, 24 pushes in 1 year 2 months
Contributions summary:Rinon's contributions primarily involve modifications to a Jupyter Notebook (`stylegan_nada.ipynb`) related to the `stylegan-nada` project. These modifications include fixing a repository token, updating training parameters such as the number of iterations and save intervals, adding support for saving checkpoints in Colab, and incorporating support for targeting styles from images and videos. These changes suggest a focus on improving the usability, functionality, and integration of the StyleGAN-NADA model within a Colab environment, specifically targeting domain adaptation.
stylegandomain-adaptationgenerative-adversarial-network
rinongal/textual_inversion
Aug 2022 - Nov 2022
Contributions:12 commits, 3 PRs, 10 pushes in 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.