Tobias Pfaff

🦛

Tobias Pfaff

Research Scientist

About Me

I am a staff research scientist with Google DeepMind. My current research focus is AI4Science, in particular learned physics simulators, and generative video models.

I wasn’t always in machine learning. I used to be a computer graphics researcher, writing fluid, cloth & fracture solvers for SFX; did some geophysics, pondering about permafrost soils in Tibet; worked at a SF startup with a ridiculously bad business idea; and did a stint in video game development as well. To my utter surprise, this weird trajectory has somehow worked out well!

I am also a proud dad, cat owner, and hippo enthusiast. My car is a cargo bike.

Selected Publications

See Google Scholar for the full set of my publications.

Imagen 3.
The Imagen Team.
arXiv 2024.

PDF Cite Project

Learning rigid-body simulators over implicit shapes.
Y Rubanova, T Lopez-Guevara, KR Allen, WF Whitney, K Stachenfeld, T Pfaff.
NeurIPS 2024 [oral].

PDF Cite Project

Graph network simulators can learn discontinuous, rigid contact dynamics.
KR Allen, T Lopez, Y Rubanova, K Stachenfeld, A Sanchez, P Battaglia, T Pfaff.
CoRL 2023.

PDF Cite Project

Learning 3D Particle-based Simulators from RGB-D Videos.
WF Whitney, T Lopez, T Pfaff, Y Rubanova, T Kipf, K Stachenfeld, KR Allen.
ICLR 2024.

PDF Cite Project

Learning rigid dynamics with face interaction graph networks.
KR Allen, Y Rubanova, T Lopez, W Whitney, A Sanchez, P Battaglia, T Pfaff.
ICLR 2023.

PDF Cite Project

Multiscale meshgraphnets.
M Fortunato, T Pfaff, P Wirnsberger, A Pritzel, P Battaglia.
arXiv 2022.

PDF Cite

Physical Design using Differentiable Learned Simulators.
KR Allen, T Lopez, K Stachenfeld, A Sanchez, P Battaglia, J Hamrick, T Pfaff.
NeurIPS 2022.

PDF Cite Project