no code implementations • 14 Feb 2024 • Simon Geisler, Tom Wollschläger, M. H. I. Abdalla, Johannes Gasteiger, Stephan Günnemann
Current LLM alignment methods are readily broken through specifically crafted adversarial prompts.
1 code implementation • 16 Aug 2023 • Francesco Campi, Lukas Gosch, Tom Wollschläger, Yan Scholten, Stephan Günnemann
We perform the first adversarial robustness study into Graph Neural Networks (GNNs) that are provably more powerful than traditional Message Passing Neural Networks (MPNNs).
no code implementations • 20 Jun 2023 • Tom Wollschläger, Nicholas Gao, Bertrand Charpentier, Mohamed Amine Ketata, Stephan Günnemann
Graph Neural Networks (GNNs) are promising surrogates for quantum mechanical calculations as they establish unprecedented low errors on collections of molecular dynamics (MD) trajectories.
1 code implementation • 30 Apr 2023 • Nicola Franco, Tom Wollschläger, Benedikt Poggel, Stephan Günnemann, Jeanette Miriam Lorenz
We conduct a detailed analysis for the decomposition of MILP with Benders and Dantzig-Wolfe methods.
no code implementations • 28 Oct 2022 • Jan Schuchardt, Tom Wollschläger, Aleksandar Bojchevski, Stephan Günnemann
We further show that this approach is beneficial for the larger class of softly local models, where each output is dependent on the entire input but assigns different levels of importance to different input regions (e. g. based on their proximity in the image).