Publications

Benedikt Alkin, Maximilian Beck, Korbinian Poeppel, Sepp Hochreiter, Johannes Brandstetter (2024). Vision-LSTM -- xLSTM as Generic Vision Backbone. Preprint.

PDF Cite Code Project

Cristian Bodnar, Wessel W. Bruinsma, Ana Lucic, Megan Stanley, Johannes Brandstetter, Patrick Garvan, Maik Riechert, Jonathan Weyn, Haiyu Dong, Anna Vaughan, Jayesh K. Gupta, Kit Tambiratnam, Alex Archibald, Elizabeth Heider, Max Welling, Rich E. Turner, Paris Perdikaris (2024). Aurora -- A foundation Model of the Atmosphere. Preprint.

PDF Cite

Maximilian Beck, Korbinian Poeppel, Markus Spanring, Andreas Auer, Oleksandra Prudnikova, Michael Kopp, Günter Klambauer, Johannes Brandstetter, Sepp Hochreiter (2024). xLSTM -- Extended Long Short-Term Memory. Preprint.

PDF Cite Code

Arturs Berzins, Andreas Radler, Sebastian Sanokowski, Sepp Hochreiter, Johannes Brandstetter (2024). Geometry-Informed Neural Networks. Preprint.

PDF Cite Code Project

Benedikt Alkin, Andreas Fürst, Simon Schmid, Lukas Gruber, Markus Holzleitner, Johannes Brandstetter (2024). Universal Physics Transformers -- A Framework For Efficiently Scaling Neural Operators. Preprint.

PDF Cite Code Project

Benedikt Alkin, Lukas Miklautz, Sepp Hochreiter, Johannes Brandstetter (2024). Mim-refiner -- A contrastive learning boost from intermediate pre-trained representations. Preprint.

PDF Cite Code Project

Artur P. Toshev, Jonas A. Erbesdobler, Nikolaus A. Adams, Johannes Brandstetter (2024). We identify particle clustering originating from tensile instabilities as one of the primary pitfalls. Based on these insights, we enhance both training and rollout inference of GNN-based simulators with varying components from standard SPH solvers, including pressure, viscous, and external force components.. 41th International Conference on Machine Learning (ICML), 2024.

PDF Cite Code Project Poster

Tara Akhound-Sadegh, Laurence Perreault-Levasseur, Johannes Brandstetter, Max Welling, Siamak Ravanbakhsh (2023). Lie Point Symmetries and Physics-Informed Networks. Thirty-seventh Conference on Neural Information Processing Systems (NeurIPS), 2023.

PDF Cite

Phillip Lippe, Bastiaan S. Veeling, Paris Perdikaris, Richard E. Turner, Johannes Brandstetter (2023). PDE-Refiner - Achieving Accurate Long Rollouts with Neural PDE Solvers. Thirty-seventh Conference on Neural Information Processing Systems (NeurIPS), 2023 (Spotlight).

PDF Cite Code Project Poster Slides Video

Artur P. Toshev, Gianluca Galletti, Johannes Brandstetter, Stefan Adami, Nikolaus A. Adams (2023). Learning Lagrangian Fluid Mechanics with E(3)-Equivariant Graph Neural Networks. 6th International Conference on Geometric Science of Information (GSI), 2023.

PDF Cite Code

David Ruhe, Johannes Brandstetter, Patrick Forré (2023). Clifford Group Equivariant Neural Networks. Thirty-seventh Conference on Neural Information Processing Systems (NeurIPS), 2023 (Oral).

PDF Cite Code Blog post

David Ruhe, Jayesh K. Gupta, Steven De Keninck, Max Welling, Johannes Brandstetter (2023). Geometric Clifford Algebra Networks. 40th International Conference on Machine Learning (ICML), 2023.

PDF Cite Code Project Poster Blog post

Tung Nguyen, Johannes Brandstetter, Ashish Kapoor, Jayesh K. Gupta, Aditya Grover (2023). ClimaX -- A foundation model for weather and climate. 40th International Conference on Machine Learning (ICML), 2023 (Spotlight).

PDF Cite Code Project

Jayesh K. Gupta, Johannes Brandstetter (2022). Towards Multi-spatiotemporal-scale Generalized PDE Modeling. Transactions on Machine Learning (TMLR), 07/2023.

PDF Cite Code Project

Johannes Brandstetter, Rianne Van Den Berg, Max Welling, Jayesh Gupta (2022). Clifford Neural Layers for PDE Modeling. 11th International Conference on Learning Representations (ICLR), 2023.

PDF Cite Code Project Poster Slides Blog post

Johannes Brandstetter, Max Welling, Daniel E. Worrall (2022). Lie Point Symmetry Data Augmentation for Neural PDE Solvers. 39th International Conference on Machine Learning (ICML), 2022 (Spotlight).

PDF Cite Code Poster Slides

Johannes Brandstetter, Daniel E. Worrall, Max Welling (2022). Message Passing Neural PDE Solvers. 10th International Conference on Learning Representations (ICLR), 2022 (Spotlight).

PDF Cite Code Poster Slides

Johannes Brandstetter, Rob Hesselink, Elise Van Der Pol, Erik Bekkers, Max Welling (2021). Geometric and Physical Quantities Improve E(3) Equivariant Message Passing. 10th International Conference on Learning Representations (ICLR), 2022 (Spotlight).

PDF Cite Code Poster Slides Blog post

Andreas Mayr, Sebastian Lehner, Arno Mayrhofer, Christoph Kloss, Sepp Hochreiter, Johannes Brandstetter (2021). Boundary Graph Neural Networks for 3D Simulations. 37th AAAI Conference on Artificial Intelligence (AAAI), 2023.

PDF Cite Code Poster Blog post

Johannes Brandstetter, Hubert Ramsauer, Markus Holzleitner, Sepp Hochreiter, Bernhard Schäfl (2020). Looking at the Performer from a Hopfield point of view. 10th International Conference on Learning Representations (ICLR), 2022 (Blogpost).

Blog post

Markus Holzleitner, Lukas Gruber, José A. Arjona-Medina, Johannes Brandstetter, Sepp Hochreiter (2020). Convergence proof for actor-critic methods applied to ppo and rudder. Transactions on Large-Scale Data-and Knowledge-Centered Systems XLVIII, 2021.

PDF Cite

Vihang Patil, Markus Hofmarcher, Marius-Constantin Dinu, Matthias Dorfer, Patrick Blies, Johannes Brandstetter, José A. Arjona-Medina, Sepp Hochreiter (2020). Align-RUDDER -- Learning From Few Demonstrations by Reward Redistribution. 39th International Conference on Machine Learning (ICML), 2022 (Oral).

PDF Cite Code Poster Slides Blog post

Hubert Ramsauer, Bernhard Schäfl, Johannes Lehner, Philipp Seidl, Michael Widrich, Thomas Adler, Lukas Gruber, Markus Holzleitner, Milena Pavlović, Geir Kjetil Sandve, Victor Greiff, David Kreil, Michael Kopp, Günter Klambauer, Johannes Brandstetter, Sepp Hochreiter (2020). Hopfield Networks is All You Need. 9th International Conference on Learning Representations (ICLR), 2021.

PDF Cite Code Blog post

Michael Widrich, Bernhard Schäfl, Milena Pavlović, Hubert Ramsauer, Lukas Gruber, Markus Holzleitner, Johannes Brandstetter, Geir Kjetil Sandve, Victor Greiff, Sepp Hochreiter, Günter Klambauer (2020). Modern hopfield networks and attention for immune repertoire classification. Thirty-third Conference on Neural Information Processing Systems (NeurIPS), 2020 (Spotlight).

PDF Cite Code Poster Blog post

Johannes Brandstetter, CMS Collaboration (2018). Combined measurements of Higgs boson couplings in proton-proton collisions at $\sqrt{s}=$ 13 TeV. Eur. Phys. J. C 79 (2019) 42.

PDF Cite

José A. Arjona-Medina, Michael Gillhofer, Michael Widrich, Thomas Unterthiner, Johannes Brandstetter, Sepp Hochreiter (2018). RUDDER -- Return Decomposition for Delayed Rewards. Thirty-second Conference on Neural Information Processing Systems (NeurIPS), 2019.

PDF Cite Code Poster Blog post

Johannes Brandstetter, CMS Collaboration (2018). Search for a singly produced third-generation scalar leptoquark decaying to a $\tau$ lepton and a bottom quark in proton-proton collisions at $\sqrt{s}=$ 13 TeV. JHEP 07 (2018) 115.

PDF Cite

Johannes Brandstetter (2018). Neutral Higgs boson and Z boson decays into pairs of tau leptons with the CMS detector. CERN-THESIS-2018-066.

PDF Cite

Johannes Brandstetter, CMS Collaboration (2018). Search for additional neutral MSSM Higgs bosons in the $\tau\tau$ final state in proton-proton collisions at $\sqrt{s}=$ 13 TeV. Journal of High Energy Physics (2018).

PDF Cite

Johannes Brandstetter, CMS Collaboration (2018). Measurement of the $Z/ \gamma^* \rightarrow \tau \tau$ cross section in pp collisions at $\sqrt{s}=$ 13 TeV and validation of $\tau$ lepton analysis techniques. Eur. Phys. J. C 78 (2018) 708.

PDF Cite

Johannes Brandstetter, CMS Collaboration (2017). Observation of the Higgs boson decay to a pair of tau leptons with the CMS detector. Phys. Lett. B 779 (2018) 283.

PDF Cite