Tobias Pfaff

Researcher. Game programmer. Stingray enthusiast.

My full set of publications can be found in Google Scholar.

Selected Publications

Google Veo

The GenMedia Veo team

Learning rigid-body simulators over implicit shapes for large-scale scenes and vision

Yulia Rubanova, Tatiana Lopez-Guevara, Kelsey Allen, William Whitney, Kim Stachenfeld, Tobias Pfaff

Learning 3D Particle-based Simulators from RGB-D Videos

William Whitney*, Tatiana Lopez-Guevara*, Tobias Pfaff, Yulia Rubanova, Thomas Kipf, Kim Stachenfeld, Kelsey Allen
ICLR 2024

Learning rigid dynamics with face interaction graph networks

Kelsey Allen*, Yulia Rubanova*, Tatiana Lopez-Guevara, William Whitney, Alvaro Sanchez-Gonzalez, Peter Battaglia, Tobias Pfaff
ICLR 2023

Physical Design using Differentiable Learned Simulators

Kelsey Allen* & Tatiana Lopez Guevara* & Kim Stachenfeld*, Alvaro Sanchez-Gonzalez, Jessica Hamrick, Tobias Pfaff
NeurIPS 2022

Graph network simulators can learn discontinuous, rigid contact dynamics

Kelsey Allen, Tatiana Lopez Guevara, Yulia Rubanova, Kim Stachenfeld, Alvaro Sanchez-Gonzalez, Peter Battaglia, Tobias Pfaff
CoRL 2022

Multiscale MeshGraphNets

Meire Fortunato* & Tobias Pfaff*, Peter Wirnsberger, Alexander Pritzel, Peter Battaglia
ICML 2022 AI4Science Workshop

Constraint-based graph network simulator

Yulia Rubanova* & Alvaro Sanchez-Gonzalez*, Tobias Pfaff, Peter Battaglia
ICML 2022

Learned Coarse Models for Efficient Turbulence Simulation

Kim Stachenfeld, Drummond Fielding, Dmitrii Kochkov, Miles Cranmer, Tobias Pfaff, Jonathan Godwin, Can Cui, Shirely Ho, Peter Battaglia, Alvaro Sanchez-Gonzalez
ICLR 2022

Predicting Physics in Mesh-reduced Space with Temporal Attention

Xu Han* & Han Gao* & Tobias Pfaff, Jian-Xun Wang, Li-Ping Liu
ICLR 2022

Learning Mesh-Based Simulation with Graph Networks

Tobias Pfaff* & Meire Fortunato* & Alvaro Sanchez-Gonzalez*, Peter Battaglia
ICLR 2021 (Outstanding paper award)

Learning to Simulate Complex Physics with Graph Networks

Alvaro Sanchez-Gonzalez* & Jonathan Godwin* & Tobias Pfaff* & Rex Ying*, Jure Leskovec, Peter Battaglia
ICML 2020

Combining Q-Learning and Search with Amortized Value Estimates

Jessica B. Hamrick, Victor Bapst, Alvaro Sanchez-Gonzalez, Tobias Pfaff, Théophane Weber, Lars Buesing, Peter Battaglia
ICLR 2020

Grandmaster level in StarCraft II using multi-agent reinforcement learning

The AlphaStar team
Nature, 2019

One-shot high-fidelity imitation: Training large-scale deep nets with RL

Tom Le Paine* & Sergio Gómez Colmenarejo*, Ziyu Wang, Scott Reed, Yusuf Aytar, Tobias Pfaff, Matt Hoffman, Gabriel Barth-Maron, Serkan Cabi, David Budden, Nando de Freitas
Arxiv, 2018

Playing hard exploration games by watching YouTube

Yusuf Aytar* & Tobias Pfaff*, David Budden, Tom Le Paine, Ziyu Wang, Nando de Freitas
NeurIPS 2018 (Spotlight paper)

Adaptive Tearing and Cracking of Thin Sheets

Tobias Pfaff, Rahul Narain, Juan de Joya, James O’Brien

Folding and Crumpling Adaptive Sheets

Rahul Narain, Tobias Pfaff, James O’Brien

Lagrangian Vortex Sheets for Fluid Animation

Tobias Pfaff, Nils Thürey, Markus Gross

Scalable Fluid Simulation using Anisotropic Turbulence Particles

Tobias Pfaff, Nils Thürey, Jonathan Cohen, Sarah Tariq, Markus Gross

Synthetic Turbulence using Artificial Boundary Layers

Tobias Pfaff, Nils Thürey, Andrew Selle, Markus Gross

Field-scale apparent hydraulic parameterisation obtained
from TDR time series and inverse modelling

Ute Wollschläger, Tobias Pfaff, Kurt Roth
Hydrology and Earth System Sciences, 2009


Detail Enhancement for Fluid Simulation using Turbulence Modeling

Ph.D. Thesis
CS Department, ETH Zurich, October 2012
Referents: Markus Gross, Nils Thürey, Ronald Peikert, James O'Brien

Monitoring and Analysis of Transport Processes with ERT

Diploma (M.Sc.) Thesis
Institute for Environmental Physics, Heidelberg, October 2007
Referents: Kurt Roth, Peter Nielaba, Wolfgang Dieterich
Don't panic: while the title and abstract are in German, the actual thesis is in English