Skip to content

Matthias Bethge

Publication record assembled from the DBLP archive of ranked conferences.

Papers indexed

42

Venues

11

Active years

2015–2026

Best venue rank

A*

Where they publish

Papers

42 indexed papers, newest first.

YearVenueTitleAuthors
2026WACVIsolating the Role of Temporal Information in Video Saliency: A Controlled Experimental Analysis.Peter El-Jiz, Matthias Kmmerer, Matthias Tangemann, Matthias Bethge, Andreas M. Bartels, Michael M. Bannert
2025ACLONEBench to Test Them All: Sample-Level Benchmarking Over Open-Ended Capabilities.Adhiraj Ghosh, Sebastian Dziadzio, Ameya Prabhu, Vishaal Udandarao, Samuel Albanie, Matthias Bethge
2025CVPRHow to Merge Your Multimodal Models Over Time?Sebastian Dziadzio, Vishaal Udandarao, Karsten Roth, Ameya Prabhu, Zeynep Akata, Samuel Albanie, Matthias Bethge
2025ICCVModeling Saliency Dataset Bias.Matthias Kmmerer, Harneet Singh Khanuja, Matthias Bethge
2025ICCVVGGSounder: Audio-Visual Evaluations for Foundation Models.Daniil Zverev, Thaddus Wiedemer, Ameya Prabhu, Matthias Bethge, Wieland Brendel, A. Sophia Koepke
2025ICLRIdentifying latent state transitions in non-linear dynamical systems.aglar Hizli, agatay Yildiz, Matthias Bethge, S. T. John, Pekka Marttinen
2025ICLRIn Search of Forgotten Domain Generalization.Prasanna Mayilvahanan, Roland S. Zimmermann, Thaddus Wiedemer, Evgenia Rusak, Attila Juhos, Matthias Bethge, Wieland Brendel
2025ICMLTesting the Limits of Fine-Tuning for Improving Visual Cognition in Vision Language Models.Luca M. Schulze Buschoff, Konstantinos Voudouris, Elif Akata, Matthias Bethge, Joshua B. Tenenbaum, Eric Schulz
2025ICMLGreat Models Think Alike and this Undermines AI Oversight.Shashwat Goel, Joschka Strber, Ilze Amanda Auzina, Karuna K. Chandra, Ponnurangam Kumaraguru, Douwe Kiela, Ameya Prabhu, Matthias Bethge, Jonas Geiping
2025ICMLLLMs on the Line: Data Determines Loss-to-Loss Scaling Laws.Prasanna Mayilvahanan, Thaddus Wiedemer, Sayak Mallick, Matthias Bethge, Wieland Brendel
2025ICMLWikiBigEdit: Understanding the Limits of Lifelong Knowledge Editing in LLMs.Lukas Thede, Karsten Roth, Matthias Bethge, Zeynep Akata, Thomas Hartvigsen
2024EMNLPAdaptation Odyssey in LLMs: Why Does Additional Pretraining Sometimes Fail to Improve?Firat ncel, Matthias Bethge, Beyza Ermis, Mirco Ravanelli, Cem Subakan, agatay Yildiz
2024ICLRMost discriminative stimuli for functional cell type clustering.Max F. Burg, Thomas Zenkel, Michaela Vystrcilov, Jonathan Oesterle, Larissa Hfling, Konstantin F. Willeke, Jan Lause, Sarah Mller, Paul G. Fahey, Zhiwei Ding, Kelli Restivo, Shashwat Sridhar, Tim Gollisch, Philipp Berens, Andreas S. Tolias, Thomas Euler, Matthias Bethge, Alexander S. Ecker
2024ICLRDoes CLIP's generalization performance mainly stem from high train-test similarity?Prasanna Mayilvahanan, Thaddus Wiedemer, Evgenia Rusak, Matthias Bethge, Wieland Brendel
2024ICLRVisual Data-Type Understanding does not emerge from scaling Vision-Language Models.Vishaal Udandarao, Max F. Burg, Samuel Albanie, Matthias Bethge
2024ICLRProvable Compositional Generalization for Object-Centric Learning.Thaddus Wiedemer, Jack Brady, Alexander Panfilov, Attila Juhos, Matthias Bethge, Wieland Brendel
2024ICMLThe Entropy Enigma: Success and Failure of Entropy Minimization.Ori Press, Ravid Shwartz-Ziv, Yann LeCun, Matthias Bethge
2024VISIGRAPPScale Learning in Scale-Equivariant Convolutional Networks.Mark Basting, Robert-Jan Bruintjes, Thaddus Wiedemer, Matthias Kmmerer, Matthias Bethge, Jan van Gemert
2022ICLRVisual Representation Learning Does Not Generalize Strongly Within the Same Domain.Lukas Schott, Julius von Kgelgen, Frederik Truble, Peter Vincent Gehler, Chris Russell, Matthias Bethge, Bernhard Schlkopf, Francesco Locatello, Wieland Brendel
2021ICCVDeepGaze IIE: Calibrated prediction in and out-of-domain for state-of-the-art saliency modeling.Akis Linardos, Matthias Kmmerer, Ori Press, Matthias Bethge
2021ICLRExemplary Natural Images Explain CNN Activations Better than State-of-the-Art Feature Visualization.Judy Borowski, Roland Simon Zimmermann, Judith Schepers, Robert Geirhos, Thomas S. A. Wallis, Matthias Bethge, Wieland Brendel
2021ICLRTowards Nonlinear Disentanglement in Natural Data with Temporal Sparse Coding.David A. Klindt, Lukas Schott, Yash Sharma, Ivan Ustyuzhaninov, Wieland Brendel, Matthias Bethge, Dylan M. Paiton
2021ICMLContrastive Learning Inverts the Data Generating Process.Roland S. Zimmermann, Yash Sharma, Steffen Schneider, Matthias Bethge, Wieland Brendel
2021WACVPretraining boosts out-of-domain robustness for pose estimation.Alexander Mathis, Thomas Biasi, Steffen Schneider, Mert Yksekgnl, Byron Rogers, Matthias Bethge, Mackenzie W. Mathis
2020ECCVA Simple Way to Make Neural Networks Robust Against Diverse Image Corruptions.Evgenia Rusak, Lukas Schott, Roland S. Zimmermann, Julian Bitterwolf, Oliver Bringmann, Matthias Bethge, Wieland Brendel
2020ECCVMeasuring the Importance of Temporal Features in Video Saliency.Matthias Tangemann, Matthias Kmmerer, Thomas S. A. Wallis, Matthias Bethge
2020GIKnstliche Intelligenz - Die dritte Welle.Ute Schmid, Volker Tresp, Matthias Bethge, Kristian Kersting, Rainer Stiefelhagen
2020ICLRRotation-invariant clustering of neuronal responses in primary visual cortex.Ivan Ustyuzhaninov, Santiago A. Cadena, Emmanouil Froudarakis, Paul G. Fahey, Edgar Y. Walker, Erick Cobos, Jacob Reimer, Fabian H. Sinz, Andreas S. Tolias, Matthias Bethge, Alexander S. Ecker
2019ICLRApproximating CNNs with Bag-of-local-Features models works surprisingly well on ImageNet.Wieland Brendel, Matthias Bethge
2019ICLRA rotation-equivariant convolutional neural network model of primary visual cortex.Alexander S. Ecker, Fabian H. Sinz, Emmanouil Froudarakis, Paul G. Fahey, Santiago A. Cadena, Edgar Y. Walker, Erick Cobos, Jacob Reimer, Andreas S. Tolias, Matthias Bethge
2019ICLRImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness.Robert Geirhos, Patricia Rubisch, Claudio Michaelis, Matthias Bethge, Felix A. Wichmann, Wieland Brendel
2019ICLRExcessive Invariance Causes Adversarial Vulnerability.Jrn-Henrik Jacobsen, Jens Behrmann, Richard S. Zemel, Matthias Bethge
2019ICLRTowards the first adversarially robust neural network model on MNIST.Lukas Schott, Jonas Rauber, Matthias Bethge, Wieland Brendel
2018ECCVDiverse Feature Visualizations Reveal Invariances in Early Layers of Deep Neural Networks.Santiago A. Cadena, Marissa A. Weis, Leon A. Gatys, Matthias Bethge, Alexander S. Ecker
2018ECCVSaliency Benchmarking Made Easy: Separating Models, Maps and Metrics.Matthias Kmmerer, Thomas S. A. Wallis, Matthias Bethge
2018ICLRDecision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Models.Wieland Brendel, Jonas Rauber, Matthias Bethge
2018ICMLOne-Shot Segmentation in Clutter.Claudio Michaelis, Matthias Bethge, Alexander S. Ecker
2017CVPRControlling Perceptual Factors in Neural Style Transfer.Leon A. Gatys, Alexander S. Ecker, Matthias Bethge, Aaron Hertzmann, Eli Shechtman
2017ICCVUnderstanding Low- and High-Level Contributions to Fixation Prediction.Matthias Kmmerer, Thomas S. A. Wallis, Leon A. Gatys, Matthias Bethge
2017ICLRWhat does it take to generate natural textures?Ivan Ustyuzhaninov, Wieland Brendel, Leon A. Gatys, Matthias Bethge
2016CVPRImage Style Transfer Using Convolutional Neural Networks.Leon A. Gatys, Alexander S. Ecker, Matthias Bethge
2015AISTATSData modeling with the elliptical gamma distribution.Suvrit Sra, Reshad Hosseini, Lucas Theis, Matthias Bethge