Yulia Rubanova

yulia_photo.JPG

Senior Research Scientist, Google Deepmind • Previously: UofT


I am currently working on Veo generative model for video. Overall, I am interested in making image- and video- generative models that are controllable and physically-realistic.

  • controlling object location, pose and appearance in generated videos
  • physically realistic interactions between objects in video
  • object discovery, extracting 3D information from images and video
  • using generative models as world models for robotics

Previously, I worked on Learning Simulation – learning to simulate object collisions in 3D using using graph neural networks.

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 a few internships at Google Brain working on optimization of discrete objects in 2019-2020 and DeepVariant in 2018.

Selected publications

  1. neural_assets.gif
    Neural Assets: 3D-Aware Multi-Object Scene Synthesis with Image Diffusion Models
    Ziyi Wu, Yulia Rubanova, Rishabh Kabra, Drew A. Hudson, Igor Gilitschenski, Yusuf Aytar, Sjoerd Steenkiste, Kelsey R. Allen, and Thomas Kipf
    2024
  2. sdf_sim.gif
    Learning rigid-body simulators over implicit shapes for large-scale scenes and vision
    Yulia Rubanova, Tatiana Lopez-Guevara, Kelsey R. Allen, William F. Whitney, Kimberly Stachenfeld, and Tobias Pfaff
    2024
  3. vpd.gif
    Learning 3D Particle-based Simulators from RGB-D Videos
    William F Whitney, Tatiana Lopez-Guevara, Tobias Pfaff, Yulia Rubanova, Thomas Kipf, Kim Stachenfeld, and Kelsey R Allen
    The Twelfth International Conference on Learning Representations, 2024
  4. FIGNet_0002.gif
    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
  5. constraint.png
    Constraint-based graph network simulator
    Yulia Rubanova*, Alvaro Sanchez-Gonzalez*, Tobias Pfaff, and Peter Battaglia
    ICML, 2022
  6. latent_ode.png
    Latent Ordinary Differential Equations for Irregularly-Sampled Time Series
    Yulia Rubanova, Ricky T. Q. Chen, and David K Duvenaud
    NeurIPS, 2019
  7. neural_ode.png
    Neural Ordinary Differential Equations
    Ricky T. Q. Chen*, Yulia Rubanova*, Jesse Bettencourt, and David Duvenaud
    NeurIPS, 2018