Rameen Abdal
Research Scientist at Snap Inc.
Palo Alto, California, United States
Summary
🤩
Rockstar🎓
Top SchoolRameen Abdal is a research scientist in Palo Alto with nine years of experience specializing in generative modeling and personalized image and video synthesis, currently working on GenAI and video personalization at Snap. He earned an MS and PhD in Computer Science from KAUST and has held research roles at Stanford, Adobe, and Snap, blending deep learning research with practical engineering. Rameen contributed as an ML engineer to the influential StyleFlow project—enabling attribute-conditioned exploration of StyleGAN outputs—by implementing training pipelines and improving project documentation. His work spans images, videos and 3D, and he often bridges academic rigor with production-focused tooling and reproducible code. An educator-turned-researcher, he also taught deep learning for visual computing and maintains an accessible personal site showcasing his research and code.
9 years of coding experience
Doctor of Philosophy - PhD Computer Science, Doctor of Philosophy - PhD Computer Science at KAUST (King Abdullah University of Science and Technology)High School Science, High School Science at Tyndale Biscoe School, SrinagarBachelor of Technology Electronics and Communications Engineering, Bachelor of Technology Electronics and Communications Engineering at National Institute of Technology Srinagar
English, Urdu, Hindi, Kashmiri
Stackoverflow
1reputation
0reached
0answers
0questions
Github Skills (8)
pytorch10
machine-learning10
stylegan10
python10
documentation7
quality-assurance6
data-quality6
software-quality6
Programming languages (1)
Github contributions (5)
RameenAbdal/StyleFlow
Jan 2021 - Jan 2023
StyleFlow: Attribute-conditioned Exploration of StyleGAN-generated Images using Conditional Continuous Normalizing Flows (ACM TOG 2021)
Role in this project:
ML Engineer
ML EngineerContributions:40 commits, 1 PR, 361 pushes in 2 years
Contributions summary:Rameen primarily focused on modifying the training script (`train_flow.py`) for the StyleFlow model. They implemented training procedures, including defining the dataset, optimizer, and loss function. Furthermore, the user updated the project's documentation, specifically the `default.html` file, refining the presentation of the project details, author information, and links to relevant resources such as the paper, code repository, and video.
normalizing-flowsacmcycleganoptical-flowcontinuous
RameenAbdal/Labels4Free
Mar 2021 - Jan 2023
https://rameenabdal.github.io/Labels4Free/ (ICCV 2021)
Contributions:41 commits, 36 pushes, 2 comments in 1 year 9 months
deep-learningpytorchiccvcomputer-vision
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.