Yuval Alaluf
Member Of Technical Staff at Runway
Tel-Aviv District, Israel
Summary
🤩
Rockstar🎓
Top SchoolYuval Alaluf is a Research Scientist and Member of Technical Staff with seven years of experience specializing in generative AI and computer vision, currently based in Tel Aviv. He has held research and engineering roles at Runway, Pika, and Snap, and led R&D teams in the Israel Defense Forces, blending product-focused research with applied deployment. His open-source contributions include official implementations for influential StyleGAN encoder papers (ReStyle, pSp, SAM), showing deep expertise in model architecture and practical inference tooling. Yuval pairs a strong academic foundation—ongoing PhD and MSc work at Tel Aviv University—with hands-on engineering that integrates pre-trained models, iterative refinement, and web-ready replication scripts. He is notable for translating cutting-edge academic methods into usable code that accelerates image editing and age-transformation workflows. Colleagues rely on him for bridging rigorous research with production-ready ML engineering.
7 years of coding experience
6 years of employment as a software developer
Doctor of Philosophy - PhD, Computer Science, Doctor of Philosophy - PhD, Computer Science at Tel Aviv UniversityBachelor of Science - BS, Computer Science, Bachelor of Science - BS, Computer Science at Reichman University
English, Hebrew
Stackoverflow
1reputation
0reached
0answers
0questions
Github Skills (14)
computer-vision10
pytorch10
machine-learning10
stylegan10
jupyter-notebook10
python10
generative-adversarial-network10
image-processing10
image-manipulation9
image-translation9
mlops8
docker6
dockers6
tensorflow3
Programming languages (2)
Github contributions (5)
eladrich/pixel2style2pixel
Oct 2020 - Oct 2022
Official Implementation for "Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation" (CVPR 2021) presenting the pixel2style2pixel (pSp) framework
Role in this project:
ML Engineer
ML EngineerContributions:3 reviews, 47 commits, 3 PRs in 2 years
Contributions summary:Yuval primarily contributed to the core model files, including the definition of the `PixelNorm`, `Upsample`, `Downsample`, `Blur`, `EqualConv2d`, `StyledConv`, and other related modules. The user added, modified and updated code related to the StyleGAN2 model's architecture, which is used within the pixel2style2pixel framework. The commits show significant work related to the core model's building blocks.
stylegancycleganimage-synthesistranslationgenerative-adversarial-network
yuval-alaluf/restyle-encoder
Apr 2021 - Oct 2022
Official Implementation for "ReStyle: A Residual-Based StyleGAN Encoder via Iterative Refinement" (ICCV 2021) https://arxiv.org/abs/2104.02699
Role in this project:ML Engineer
ML EngineerContributions:41 commits, 6 PRs, 38 pushes in 1 year 6 months
Contributions summary:Yuval primarily contributes to the development and maintenance of a StyleGAN-based encoder for image manipulation, specifically focused on Restyle, as evidenced by the commit messages and code changes. Their work involves modifying the model architecture, downloading and integrating pre-trained models, and creating scripts for inference and editing. The commits demonstrate the integration of the ReStyle model with the e4e architecture and the addition of a replicate code which allows users to easily run the project from the web.
pytorchiccvstyleganarxivabs
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.