← Search

Simon Lucas Schmid

2 accepted papers

2024

Energy-based Hopfield Boosting for Out-of-Distribution Detection

NeurIPS 2024poster

Out-of-distribution (OOD) detection is critical when deploying machine learning models in the real world. Outlier exposure methods, which incorporate auxiliary outlier data in the training process, can drastically improve OOD detection performance compared to approaches without advanced training str…

2024

Universal Physics Transformers: A Framework For Efficiently Scaling Neural Operators

NeurIPS 2024poster

Neural operators, serving as physics surrogate models, have recently gained increased interest. With ever increasing problem complexity, the natural question arises: what is an efficient way to scale neural operators to larger and more complex simulations - most importantly by taking into account di…