Johannes Brandstetter

Einstein Fields: A Neural Perspective To Computational General Relativity

Physics-Preserving Compression of High-Dimensional Plasma Turbulence Simulations

From Circuits to Dynamics: Understanding and Stabilizing Failure in 3D Diffusion Transformers

SIMSHIFT: A Benchmark for Adapting Neural Surrogates to Distribution Shifts

PAINT: Parallel-in-time Neural Twins for Dynamical System Reconstruction

Stabilized Test-Time Adaptation of Neural Surrogates in Simulation

LaM-SLidE: Latent Space Modeling of Spatial Dynamical Systems via Linked Entities

MIM-Refiner: A Contrastive Learning Boost from Intermediate Pre-Trained Masked Image Modeling Representations

A Large Recurrent Action Model: xLSTM enables Fast Inference for Robotics Tasks

GyroSwin: 5D Surrogates for Gyrokinetic Plasma Turbulence Simulations

Bio-xLSTM: Generative modeling, representation and in-context learning of biological and chemical sequences

A Large Recurrent Action Model: xLSTM enables Fast Inference for Robotics Tasks

Vision-LSTM: xLSTM as Generic Vision Backbone

VN-EGNN: E(3)- and SE(3)-Equivariant Graph Neural Networks with Virtual Nodes Enhance Protein Binding Site Identification

Geometry-Informed Neural Networks

Geometry-Informed Neural Networks

UPT++: Latent Point Set Neural Operators for Modeling System State Transitions