Roland S. Zimmermann

35 papers A* 10A 1Journal 23Unranked 1

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Aligned, Orthogonal or In-conflict: When can we safely optimize Chain-of-Thought? CoRR Max Kaufmann, David Lindner, Roland S. Zimmermann, Rohin Shah
2025	J	`jnl`	A Pragmatic Way to Measure Chain-of-Thought Monitorability. CoRR Scott Emmons, Roland S. Zimmermann, David K. Elson, Rohin Shah
2025	J	`jnl`	Early Signs of Steganographic Capabilities in Frontier LLMs. CoRR Artur Zolkowski, Kei Nishimura-Gasparian, Robert McCarthy, Roland S. Zimmermann, David Lindner
2025	J	`jnl`	Evaluating Frontier Models for Stealth and Situational Awareness. CoRR Mary Phuong, Roland S. Zimmermann, Ziyue Wang, David Lindner, Victoria Krakovna, Sarah Cogan, Allan Dafoe, Lewis Ho, Rohin Shah
2025	A*	`conf`	In Search of Forgotten Domain Generalization. ICLR Prasanna Mayilvahanan, Roland S. Zimmermann, Thaddäus Wiedemer, Evgenia Rusak, Attila Juhos, Matthias Bethge, Wieland Brendel
2025	A*	`conf`	In Search of Forgotten Domain Generalization. ICLR Prasanna Mayilvahanan, Roland S. Zimmermann, Thaddäus Wiedemer, Evgenia Rusak, Attila Juhos, Matthias Bethge, Wieland Brendel
2025	A	`conf`	InfoNCE: Identifying the Gap Between Theory and Practice. AISTATS Evgenia Rusak, Patrik Reizinger, Attila Juhos, Oliver Bringmann, Roland S. Zimmermann, Wieland Brendel
2025	A*	`conf`	LAION-C: An Out-of-Distribution Benchmark for Web-Scale Vision Models. ICML Fanfei Li, Thomas Klein, Wieland Brendel, Robert Geirhos, Roland S. Zimmermann
2025	J	`jnl`	LAION-C: An Out-of-Distribution Benchmark for Web-Scale Vision Models. CoRR Fanfei Li, Thomas Klein, Wieland Brendel, Robert Geirhos, Roland S. Zimmermann
2025	J	`jnl`	Practical challenges of control monitoring in frontier AI deployments. CoRR David Lindner, Charlie Griffin, Tomek Korbak, Roland S. Zimmermann, Geoffrey Irving, Sebastian Farquhar, Alan Cooney
2024	A*	`conf`	Don't trust your eyes: on the (un)reliability of feature visualizations. ICML Robert Geirhos, Roland S. Zimmermann, Blair L. Bilodeau, Wieland Brendel, Been Kim
2024	J	`jnl`	In Search of Forgotten Domain Generalization. CoRR Prasanna Mayilvahanan, Roland S. Zimmermann, Thaddäus Wiedemer, Evgenia Rusak, Attila Juhos, Matthias Bethge, Wieland Brendel
2024	J	`jnl`	InfoNCE: Identifying the Gap Between Theory and Practice. CoRR Evgenia Rusak, Patrik Reizinger, Attila Juhos, Oliver Bringmann, Roland S. Zimmermann, Wieland Brendel
2024	A*	`conf`	Measuring Per-Unit Interpretability at Scale Without Humans. NeurIPS Roland S. Zimmermann, David A. Klindt, Wieland Brendel
2023	J	`jnl`	Don't trust your eyes: on the (un)reliability of feature visualizations. CoRR Robert Geirhos, Roland S. Zimmermann, Blair L. Bilodeau, Wieland Brendel, Been Kim
2023	A*	`conf`	Provably Learning Object-Centric Representations. ICML Jack Brady, Roland S. Zimmermann, Yash Sharma, Bernhard Schölkopf, Julius von Kügelgen, Wieland Brendel
2023	J	`jnl`	Provably Learning Object-Centric Representations. CoRR Jack Brady, Roland S. Zimmermann, Yash Sharma, Bernhard Schölkopf, Julius von Kügelgen, Wieland Brendel
2023	A*	`conf`	Scale Alone Does not Improve Mechanistic Interpretability in Vision Models. NeurIPS Roland S. Zimmermann, Thomas Klein, Wieland Brendel
2023	J	`jnl`	Scale Alone Does not Improve Mechanistic Interpretability in Vision Models. CoRR Roland S. Zimmermann, Thomas Klein, Wieland Brendel
2023	J	`jnl`	Sensitivity of Slot-Based Object-Centric Models to their Number of Slots. CoRR Roland S. Zimmermann, Sjoerd van Steenkiste, Mehdi S. M. Sajjadi, Thomas Kipf, Klaus Greff
2022	A*	`conf`	Increasing Confidence in Adversarial Robustness Evaluations. NeurIPS Roland S. Zimmermann, Wieland Brendel, Florian Tramèr, Nicholas Carlini
2022	J	`jnl`	Increasing Confidence in Adversarial Robustness Evaluations. CoRR Roland S. Zimmermann, Wieland Brendel, Florian Tramèr, Nicholas Carlini
2021	A*	`conf`	Contrastive Learning Inverts the Data Generating Process. ICML Roland S. Zimmermann, Yash Sharma, Steffen Schneider, Matthias Bethge, Wieland Brendel
2021	J	`jnl`	Contrastive Learning Inverts the Data Generating Process. CoRR Roland S. Zimmermann, Yash Sharma, Steffen Schneider, Matthias Bethge, Wieland Brendel
2021	A*	`conf`	How Well do Feature Visualizations Support Causal Understanding of CNN Activations? NeurIPS Roland S. Zimmermann, Judy Borowski, Robert Geirhos, Matthias Bethge, Thomas S. A. Wallis, Wieland Brendel
2021	J	`jnl`	How Well do Feature Visualizations Support Causal Understanding of CNN Activations? CoRR Roland S. Zimmermann, Judy Borowski, Robert Geirhos, Matthias Bethge, Thomas S. A. Wallis, Wieland Brendel
2021	J	`jnl`	Score-Based Generative Classifiers. CoRR Roland S. Zimmermann, Lukas Schott, Yang Song, Benjamin A. Dunn, David A. Klindt
2020	—	`conf`	A Simple Way to Make Neural Networks Robust Against Diverse Image Corruptions. ECCV (3) Evgenia Rusak, Lukas Schott, Roland S. Zimmermann, Julian Bitterwolf, Oliver Bringmann, Matthias Bethge, Wieland Brendel
2020	J	`jnl`	Exemplary Natural Images Explain CNN Activations Better than Feature Visualizations. CoRR Judy Borowski, Roland S. Zimmermann, Judith Schepers, Robert Geirhos, Thomas S. A. Wallis, Matthias Bethge, Wieland Brendel
2020	J	`jnl`	Increasing the robustness of DNNs against image corruptions by playing the Game of Noise. CoRR Evgenia Rusak, Lukas Schott, Roland S. Zimmermann, Julian Bitterwolf, Oliver Bringmann, Matthias Bethge, Wieland Brendel
2020	J	`jnl`	Reconstructing Complex Cardiac Excitation Waves From Incomplete Data Using Echo State Networks and Convolutional Autoencoders. Frontiers Appl. Math. Stat. Sebastian Herzog, Roland S. Zimmermann, Johannes Abele, Stefan Luther, Ulrich Parlitz
2019	J	`jnl`	Comment on "Adv-BNN: Improved Adversarial Defense through Robust Bayesian Neural Network". CoRR Roland S. Zimmermann
2019	J	`jnl`	Faster training of Mask R-CNN by focusing on instance boundaries. Comput. Vis. Image Underst. Roland S. Zimmermann, Julien N. Siems
2019	J	`jnl`	Simion Zoo: A Workbench for Distributed Experimentation with Reinforcement Learning for Continuous Control Tasks. CoRR Borja Fernández-Gauna, Manuel Graña, Roland S. Zimmermann
2018	J	`jnl`	Faster Training of Mask R-CNN by Focusing on Instance Boundaries. CoRR Roland S. Zimmermann, Julien N. Siems