Aliaksandr Siarohin
Research Scientist at Snap Inc.
Santa Monica, California, United States
Summary
🤩
Rockstar🎓
Top SchoolAliaksandr Siarohin is a research scientist in computer vision with a decade of experience focusing on image animation, video generation, 3D machine learning and generative modeling, currently based in Santa Monica and working at Snap Inc. He holds a PhD and MSc in Computer Science from the University of Trento and has published at top CV/ML conferences, bridging deep research with practical engineering. His open-source contributions include work on the influential First Order Motion Model for image animation, where he improved demos, run scripts and reproducibility. With internships at Google and Snap and earlier industry experience at Yandex and IBA Group, he blends production-facing development with cutting-edge research. Colleagues appreciate his knack for turning complex generative ideas into robust, usable code and demos.
10 years of coding experience
2 years of employment as a software developer
Bachelor's degree, Actuarial Science, Honours Degree, Bachelor's degree, Actuarial Science, Honours Degree at Belarusian State UniversityMaster's degree, Computer Science, Honours Degree, Master's degree, Computer Science, Honours Degree at UniversitĂ degli Studi di TrentoComputer Science, Computer Science at Yandex School of Data Analysis
Github Skills (4)
deep-learning10
deeplearning-ai10
python10
pytorch10
Programming languages (3)
Github contributions (5)
AliaksandrSiarohin/first-order-model
Dec 2019 - Dec 2022
This repository contains the source code for the paper First Order Motion Model for Image Animation
Role in this project:
ML Engineer
ML EngineerContributions:55 commits, 44 PRs, 69 pushes in 3 years
Contributions summary:Aliaksandr's contributions primarily involve modifications to the project's demo file and run scripts, which appear to be related to the image animation functionality. The commits show the addition of google drive links, as well as fixes of a pytorch issue and typo fixes. The user also removes a broken installation procedure.
animationdeep-learningfirst-order-motion-modelmotiongenerative-model
AliaksandrSiarohin/motion-cosegmentation
Apr 2020 - Apr 2021
Reference code for "Motion-supervised Co-Part Segmentation" paper
Contributions:8 commits, 2 PRs, 9 pushes in 1 year
pytorchstructure-from-motionsupervisedoptical-flowmotion
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.