Yulia Rubanova
I am a Research Scientist at Google Deepmind in the Structured Intelligence team led by Peter Battaglia.
Current my work is on teaching the networks to simulate the physics of the real world, as the path to make agents that are aware of the 3D world and physical interactions in it, so that they are able to reason about real objects and environments with different physical properties.
More broadly, my work is focused on fusing classic methods from physics and computer graphics into deep learning models, to make them learn more structured, efficient and interpretable represations of the real world.
I completed my PhD in University of Toronto, supervised by Quaid Morris. I worked on Neural ODE for irregularly-spaced time series (advised by David Duvenaud) and on modelling cancer evolution through time. During my PhD, I did three internships at Google Brain working on optimization of discrete objects in 2019-2020 and DeepVariant in 2018.
Selected publications
-
Reconstructing evolutionary trajectories of mutation signature activities in cancer using TrackSigNature communications, 2020