Johannes Gasteiger

23 papers A* 6A 1Journal 13Unranked 1

Year	Rank	Type	Title / Venue / Authors
2025	J	`jnl`	Natural Emergent Misalignment from Reward Hacking in Production RL. CoRR Monte MacDiarmid, Benjamin Wright, Jonathan Uesato, Joe Benton, Jonathan Kutasov, Sara Price, Naia Bouscal, Samuel R. Bowman, Trenton Bricken, Alex Cloud, Carson Denison, Johannes Gasteiger, Ryan Greenblatt, Jan Leike, Jack Lindsey, Vladimir Mikulik, Ethan Perez, Alex Rodrigues, Drake Thomas, Albert Webson, Daniel M. Ziegler, Evan Hubinger
2025	A*	`conf`	REINFORCE Adversarial Attacks on Large Language Models: An Adaptive, Distributional, and Semantic Objective. ICML Simon Geisler, Tom Wollschläger, M. H. I. Abdalla, Vincent Cohen-Addad, Johannes Gasteiger, Stephan Günnemann
2025	J	`jnl`	REINFORCE Adversarial Attacks on Large Language Models: An Adaptive, Distributional, and Semantic Objective. CoRR Simon Geisler, Tom Wollschläger, M. H. I. Abdalla, Vincent Cohen-Addad, Johannes Gasteiger, Stephan Günnemann
2025	A*	`conf`	The Geometry of Refusal in Large Language Models: Concept Cones and Representational Independence. ICML Tom Wollschläger, Jannes Elstner, Simon Geisler, Vincent Cohen-Addad, Stephan Günnemann, Johannes Gasteiger
2025	J	`jnl`	The Geometry of Refusal in Large Language Models: Concept Cones and Representational Independence. CoRR Tom Wollschläger, Jannes Elstner, Simon Geisler, Vincent Cohen-Addad, Stephan Günnemann, Johannes Gasteiger
2024	J	`jnl`	Attacking Large Language Models with Projected Gradient Descent. CoRR Simon Geisler, Tom Wollschläger, M. H. I. Abdalla, Johannes Gasteiger, Stephan Günnemann
2023	A*	`conf`	Accelerating Molecular Graph Neural Networks via Knowledge Distillation. NeurIPS Filip Ekström Kelvinius, Dimitar Georgiev, Artur P. Toshev, Johannes Gasteiger
2023	J	`jnl`	Accelerating Molecular Graph Neural Networks via Knowledge Distillation. CoRR Filip Ekström Kelvinius, Dimitar Georgiev, Artur Petrov Toshev, Johannes Gasteiger
2023	J	`jnl`	Challenges with unsupervised LLM knowledge discovery. CoRR Sebastian Farquhar, Vikrant Varma, Zachary Kenton, Johannes Gasteiger, Vladimir Mikulik, Rohin Shah
2023	J	`jnl`	Collective Robustness Certificates: Exploiting Interdependence in Graph Neural Networks. CoRR Jan Schuchardt, Aleksandar Bojchevski, Johannes Gasteiger, Stephan Günnemann
2023	A*	`conf`	Ewald-based Long-Range Message Passing for Molecular Graphs. ICML Arthur Kosmala, Johannes Gasteiger, Nicholas Gao, Stephan Günnemann
2023	J	`jnl`	Ewald-based Long-Range Message Passing for Molecular Graphs. CoRR Arthur Kosmala, Johannes Gasteiger, Nicholas Gao, Stephan Günnemann
2023	—	`—`	On the Convergence of Structure and Geometry in Graph Neural Networks. Johannes Gasteiger
2023	A	`conf`	SubMix: Learning to Mix Graph Sampling Heuristics. UAI Sami Abu-El-Haija, Joshua V. Dillon, Bahare Fatemi, Kyriakos Axiotis, Neslihan Bulut, Johannes Gasteiger, Bryan Perozzi, MohammadHossein Bateni
2023	—	`ch.`	Vereinigung von Struktur und Geometrie in Graph-Neuronalen Netzen. Ausgezeichnete Informatikdissertationen Johannes Gasteiger
2022	J	`jnl`	GemNet-OC: Developing Graph Neural Networks for Large and Diverse Molecular Simulation Datasets. Trans. Mach. Learn. Res. Johannes Gasteiger, Muhammed Shuaibi, Anuroop Sriram, Stephan Günnemann, Zachary W. Ulissi, C. Lawrence Zitnick, Abhishek Das
2022	J	`jnl`	How Do Graph Networks Generalize to Large and Diverse Molecular Systems? CoRR Johannes Gasteiger, Muhammed Shuaibi, Anuroop Sriram, Stephan Günnemann, Zachary W. Ulissi, C. Lawrence Zitnick, Abhishek Das
2022	J	`jnl`	How robust are modern graph neural network potentials in long and hot molecular dynamics simulations? Mach. Learn. Sci. Technol. Sina Stocker, Johannes Gasteiger, Florian Becker, Stephan Günnemann, Johannes T. Margraf
2022	—	`conf`	Influence-Based Mini-Batching for Graph Neural Networks. LoG Johannes Gasteiger, Chendi Qian, Stephan Günnemann
2022	J	`jnl`	Influence-Based Mini-Batching for Graph Neural Networks. CoRR Johannes Gasteiger, Chendi Qian, Stephan Günnemann
2021	A*	`conf`	Directional Message Passing on Molecular Graphs via Synthetic Coordinates. NeurIPS Johannes Gasteiger, Chandan Yeshwanth, Stephan Günnemann
2021	A*	`conf`	GemNet: Universal Directional Graph Neural Networks for Molecules. NeurIPS Johannes Gasteiger, Florian Becker, Stephan Günnemann
2021	J	`jnl`	GemNet: Universal Directional Graph Neural Networks for Molecules. CoRR Johannes Gasteiger, Florian Becker, Stephan Günnemann