7 papers
Parameter Efficient Fine-tuning via Explained Variance Adaptation
Fabian Paischer, Lukas Hauzenberger, Thomas Schmied +3
Foundation models (FMs) are pre-trained on large-scale datasets and then fine-tuned for a specific downstream task. The most common fine-tuning method is to update pretrained weigh…
AB-UPT: Scaling Neural CFD Surrogates for High-Fidelity Automotive Aerodynamics Simulations via Anchored-Branched Universal Physics Transformers
Benedikt Alkin, Maurits Bleeker, Richard Kurle +4
Recent advances in neural surrogate modeling offer the potential for transformative innovations in applications such as automotive aerodynamics. Yet, industrial-scale problems ofte…
Towards scientific machine learning for granular material simulations -- challenges and opportunities
Marc Fransen, Andreas Fürst, Deepak Tunuguntla +21
Micro-scale mechanisms, such as inter-particle and particle-fluid interactions, govern the behaviour of granular systems. While particle-scale simulations provide detailed insights…
NeuralDEM -- Real-time Simulation of Industrial Particulate Flows
Benedikt Alkin, Tobias Kronlachner, Samuele Papa +3
Advancements in computing power have made it possible to numerically simulate large-scale fluid-mechanical and/or particulate systems, many of which are integral to core industrial…
Universal Physics Transformers: A Framework For Efficiently Scaling Neural Operators
Benedikt Alkin, Andreas Fürst, Simon Schmid +3
Neural operators, serving as physics surrogate models, have recently gained increased interest. With ever increasing problem complexity, the natural question arises: what is an eff…
Vision-LSTM: xLSTM as Generic Vision Backbone
Benedikt Alkin, Maximilian Beck, Korbinian Pöppel +2
Transformers are widely used as generic backbones in computer vision, despite initially introduced for natural language processing. Recently, the Long Short-Term Memory (LSTM) has…