Roland S. Zimmermann

Affiliations:

University of Tübingen, Germany
Volkswagen AG Wolfsburg, Germany (former)
University of Göttingen, Germany (former)

According to our database¹, Roland S. Zimmermann authored at least 29 papers between 2019 and 2026.

Collaborative distances:

Dijkstra number² of four.
Erdős number³ of four.

Timeline

Legend:

Book In proceedings Article PhD thesis Dataset Other

Bibliography

2026

Exploration Hacking: Can LLMs Learn to Resist RL Training?

[BibT_eX]

[DOI]

CoRR, April, 2026

Aligned, Orthogonal or In-conflict: When can we safely optimize Chain-of-Thought?

[BibT_eX]

[DOI]

CoRR, March, 2026

2025

Practical challenges of control monitoring in frontier AI deployments.

[BibT_eX]

[DOI]

CoRR, December, 2025

A Pragmatic Way to Measure Chain-of-Thought Monitorability.

[BibT_eX]

[DOI]

CoRR, October, 2025

Early Signs of Steganographic Capabilities in Frontier LLMs.

[BibT_eX]

[DOI]

Artur Zolkowski

Kei Nishimura-Gasparian

Robert McCarthy

Roland S. Zimmermann

David Lindner

CoRR, July, 2025

Evaluating Frontier Models for Stealth and Situational Awareness.

[BibT_eX]

[DOI]

CoRR, May, 2025

Understanding Machine Perception: How Do Neural Networks Represent the World?

[BibT_eX]

[DOI]

Roland Simon Zimmermann

PhD thesis, 2025

LAION-C: An Out-of-Distribution Benchmark for Web-Scale Vision Models.

[BibT_eX]

[DOI]

Proceedings of the Forty-second International Conference on Machine Learning, 2025

In Search of Forgotten Domain Generalization.

[BibT_eX]

[DOI]

Prasanna Mayilvahanan

Proceedings of the Proceedings on "I Can't Believe It's Not Better: Challenges in Applied Deep Learning" at ICLR 2025 Workshops, 2025

InfoNCE: Identifying the Gap Between Theory and Practice.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2025

2024

Measuring Per-Unit Interpretability at Scale Without Humans.

[BibT_eX]

[DOI]

Roland S. Zimmermann

David A. Klindt

Wieland Brendel

Proceedings of the Advances in Neural Information Processing Systems 37: Annual Conference on Neural Information Processing Systems 2024, 2024

Don't trust your eyes: on the (un)reliability of feature visualizations.

[BibT_eX]

[DOI]

Proceedings of the Forty-first International Conference on Machine Learning, 2024

2023

Sensitivity of Slot-Based Object-Centric Models to their Number of Slots.

[BibT_eX]

[DOI]

Roland S. Zimmermann

Sjoerd van Steenkiste

Mehdi S. M. Sajjadi

Thomas Kipf

Klaus Greff

CoRR, 2023

Scale Alone Does not Improve Mechanistic Interpretability in Vision Models.

[BibT_eX]

[DOI]

Roland S. Zimmermann

Thomas Klein

Wieland Brendel

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Provably Learning Object-Centric Representations.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Machine Learning, 2023

2022

Increasing Confidence in Adversarial Robustness Evaluations.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

2021

Score-Based Generative Classifiers.

[BibT_eX]

[DOI]

CoRR, 2021

How Well do Feature Visualizations Support Causal Understanding of CNN Activations?

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Contrastive Learning Inverts the Data Generating Process.

[BibT_eX]

[DOI]

Proceedings of the 38th International Conference on Machine Learning, 2021

Exemplary Natural Images Explain CNN Activations Better than State-of-the-Art Feature Visualization.

[BibT_eX]

[DOI]

Judy Borowski

Roland Simon Zimmermann

Proceedings of the 9th International Conference on Learning Representations, 2021

2020

Foolbox Native: Fast adversarial attacks to benchmark the robustness of machine learning models in PyTorch, TensorFlow, and JAX.

[BibT_eX]

[DOI]

J. Open Source Softw., 2020

Reconstructing Complex Cardiac Excitation Waves From Incomplete Data Using Echo State Networks and Convolutional Autoencoders.

[BibT_eX]

[DOI]

Frontiers Appl. Math. Stat., 2020

Exemplary Natural Images Explain CNN Activations Better than Feature Visualizations.

[BibT_eX]

[DOI]

CoRR, 2020

Increasing the robustness of DNNs against image corruptions by playing the Game of Noise.

[BibT_eX]

[DOI]

CoRR, 2020

A Simple Way to Make Neural Networks Robust Against Diverse Image Corruptions.

[BibT_eX]

[DOI]

Proceedings of the Computer Vision - ECCV 2020, 2020

A Self-Supervised Feature Map Augmentation (FMA) Loss and Combined Augmentations Finetuning to Efficiently Improve the Robustness of CNNs.

[BibT_eX]

[DOI]

Proceedings of the CSCS '20: Computer Science in Cars Symposium, 2020

2019

Faster training of Mask R-CNN by focusing on instance boundaries.

[BibT_eX]

[DOI]

Roland S. Zimmermann

Julien N. Siems

Comput. Vis. Image Underst., 2019

Comment on "Adv-BNN: Improved Adversarial Defense through Robust Bayesian Neural Network".

[BibT_eX]

[DOI]

Roland S. Zimmermann

CoRR, 2019

Simion Zoo: A Workbench for Distributed Experimentation with Reinforcement Learning for Continuous Control Tasks.

[BibT_eX]

[DOI]

Borja Fernández-Gauna

Manuel Graña

Roland S. Zimmermann

CoRR, 2019

Roland S. Zimmermann

Timeline

Legend:

Links

Online presence:

On csauthors.net:

Bibliography

Loading...