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

  1. face_interaction4.png
    Learning rigid dynamics with face interaction graph networks
    Kelsey R Allen*, Yulia Rubanova*, Tatiana Lopez-Guevara, William F Whitney, Alvaro Sanchez-Gonzalez, Peter Battaglia, and Tobias Pfaff
    ICLR, 2023
  2. constraint.png
    Constraint-based graph network simulator
    Yulia Rubanova*, Alvaro Sanchez-Gonzalez*, Tobias Pfaff, and Peter Battaglia
    ICML, 2022
  3. amortised.png
    Amortized Bayesian Optimization over Discrete Spaces
    Yulia Rubanova, David Dohan, Kevin Swersky, and Kevin Murphy
    UAI, 2020
  4. tracksig.png
    Reconstructing evolutionary trajectories of mutation signature activities in cancer using TrackSig
    Yulia Rubanova, Ruian Shi, Caitlin F Harrigan, Roujia Li, Jeff Wintersinger, Nil Sahin, Amit G Deshwar, and Quaid D Morris
    Nature communications, 2020
  5. latent_ode.png
    Latent Ordinary Differential Equations for Irregularly-Sampled Time Series
    Yulia Rubanova, Ricky T. Q. Chen, and David K Duvenaud
    NeurIPS, 2019
  6. neural_ode.png
    Neural Ordinary Differential Equations
    Ricky T. Q. Chen*, Yulia Rubanova*, Jesse Bettencourt, and David Duvenaud
    NeurIPS, 2018