Yulia Rubanova
Staff Research Scientist at Google DeepMind
London, England, United Kingdom
Summary
👤
Senior🎓
Top SchoolYulia Rubanova is a Staff Research Scientist at Google DeepMind with 10 years of experience building physically grounded world models and real-time video generative systems. She co-led and was a core contributor to Veo Ingredients, helping ship Veo3.1 features including audio and enhanced character consistency showcased at Google I/O 2025. Her PhD work on Neural ODEs and Latent ODEs informs her approach to modeling continuous-time dynamics and controllable simulations for complex objects and environments. Yulia’s research spans controlling objects in image generation to learning 3D physical simulations, with a focus on moving generation toward interactive simulation for robotics, autonomous driving, and storytelling tools. Based in London, she blends deep theoretical expertise with product-impacting engineering at scale. An unexpected thread across her career is applying probabilistic and continuous-time methods—from genomics and cancer evolution to video synthesis—to make models both interpretable and controllable.
10 years of coding experience
7 years of employment as a software developer
Doctor of Philosophy - PhD Computer Science, Doctor of Philosophy - PhD Computer Science at University of Toronto
English, French, German
Github Skills (13)
infer10
inference10
time-series9
machine-learning7
r-package3
language-processing2
r2
python2
nlp1
information-retrieval1
natural-language-processing1
numpy1
retrieval1
Programming languages (2)
Github contributions (5)
morrislab/TrackSig
Dec 2016 - Jul 2019
A framework to infer mutational signatures in cancer over time
Contributions:47 commits, 7 PRs, 41 pushes in 2 years 7 months
infersignaturesmachine-learningcancermutational-signatures
YuliaRubanova/latent_ode
Jun 2019 - Dec 2020
Code for "Latent ODEs for Irregularly-Sampled Time Series" paper
Contributions:37 commits, 1 PR, 5 pushes in 1 year 5 months
time-series
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.