Staff Research Scientist · Google DeepMind
Video generationControllabilityPersonalisationPhysical reasoning
I work on Veo, including ingredient-to-video and Veo 3.1, building controllable video systems for character consistency, creative production, robotics evaluation, and physical world understanding.
My research builds toward world models that can predict, simulate, and support action in physical environments. I work on controllable video generation, learned simulation, object-centric scene structure, and robotics evaluation, with the goal of turning generative models into reliable tools for reasoning about the world.
Veo Ingredient-to-Video · Veo 3.1
Ingredient-driven video generation that preserves identity, motion, and intent.
My work connects ingredient-to-video generation, physical realism, and evaluation: from consistent characters and objects to video-based robotics simulation.
Impact: Shows Veo can become a scalable robotics evaluation environment, predicting policy rankings, out-of-distribution failures, and safety issues across 1600+ real-world trials.
Gemini Robotics Team, Coline Devin, Yilun Du, Debidatta Dwibedi, Ruiqi Gao, Abhishek Jindal, Thomas Kipf, Sean Kirmani, Fangchen Liu, Anirudha Majumdar, Andrew Marmon, Carolina Parada, Yulia Rubanova, Dhruv Shah, Vikas Sindhwani, Jie Tan, Fei Xia, Ted Xiao, Sherry Yang, Wenhao Yu, Allan Zhou
arXiv preprint, December 2025
Impact: Advances general-purpose robots with motion transfer across embodiments and multi-level reasoning, connecting world understanding to executable action.
Gemini Robotics Team
arXiv preprint, October 2025
Impact: Gives video teams a motion-sensitive evaluation tool that detects temporal failures missed by FVD and localizes where generated videos go wrong.
Kelsey Allen, Carl Doersch, Guangyao Zhou, Mohammed Suhail, Danny Driess, Ignacio Rocco, Yulia Rubanova, Thomas Kipf, Mehdi S. M. Sajjadi, Kevin Murphy, Joao Carreira, Sjoerd van Steenkiste
arXiv preprint, April 2025
Impact: Shows how diffusion models can control individual objects by appearance and 3D pose, moving image generation toward editable scene-level assets.
Ziyi Wu, Yulia Rubanova, Rishabh Kabra, Drew A. Hudson, Igor Gilitschenski, Yusuf Aytar, Sjoerd van Steenkiste, Kelsey R. Allen, Thomas Kipf
Advances in Neural Information Processing Systems 37, NeurIPS 2024
Impact: Scales learned rigid-body simulation to hundreds of objects and detailed shapes, making neural physics more plausible for real scenes.
Yulia Rubanova, Tatiana Lopez-Guevara, Kelsey R. Allen, William F. Whitney, Kimberly Stachenfeld, Tobias Pfaff
Advances in Neural Information Processing Systems 37, NeurIPS 2024
Impact: Learns editable 3D dynamics directly from observation, bridging video understanding and simulation without privileged physical state.
William F. Whitney, Tatiana Lopez-Guevara, Tobias Pfaff, Yulia Rubanova, Thomas Kipf, Kimberly Stachenfeld, Kelsey R. Allen
International Conference on Learning Representations, ICLR 2024
Impact: Makes learned simulators significantly more accurate and efficient for rigid contact, a hard case for neural physical reasoning.
Kelsey R. Allen, Yulia Rubanova, Tatiana Lopez-Guevara, William F. Whitney, Alvaro Sanchez-Gonzalez, Peter Battaglia, Tobias Pfaff
International Conference on Learning Representations, ICLR 2023
Impact: Uses learned constraints and test-time optimization to combine neural simulation with ideas from traditional physics solvers.
Yulia Rubanova, Alvaro Sanchez-Gonzalez, Tobias Pfaff, Peter Battaglia
International Conference on Machine Learning, ICML 2022
Impact: Extends continuous-time neural dynamics to irregularly sampled time series and latent-variable models.
Yulia Rubanova, Ricky T. Q. Chen, David K. Duvenaud
Advances in Neural Information Processing Systems 32, NeurIPS 2019
Impact: NeurIPS Best Paper Award winner that introduced continuous-depth neural models and helped establish differentiable dynamics as a foundation for modern ML systems.
Ricky T. Q. Chen, Yulia Rubanova, Jesse Bettencourt, David Duvenaud
Advances in Neural Information Processing Systems 31, NeurIPS 2018 · Best Paper Award