Reizinger, P., Ujváry, S., Mészáros, A., Kerekes, A., Brendel, W., Huszár, F. Position: Understanding LLMs Requires More Than Statistical Generalization Proceedings of the 41st International Conference on Machine Learning (ICML), 235, pages: 42365-42390, Proceedings of Machine Learning Research, (Editors: Salakhutdinov, Ruslan and Kolter, Zico and Heller, Katherine and Weller, Adrian and Oliver, Nuria and Scarlett, Jonathan and Berkenkamp, Felix), PMLR, July 2024 (conference)

arXiv link (url) [BibTex]

Brady*, J., Zimmermann*, R. S., Sharma, Y., Schölkopf, B., von Kügelen, J., Brendel, W. Provably Learning Object-Centric Representations Proceedings of the 40th International Conference on Machine Learning (ICML), 202, pages: 3038-3062, Proceedings of Machine Learning Research, (Editors: A. Krause, E. Brunskill, K. Cho, B. Engelhardt, S. Sabato and J. Scarlett), JMLR, Cambridge, MA, July 2023, *equal contribution (conference)

link (url) [BibTex]

Keurti, H., Reizinger, P., Schölkopf, B., Brendel, W. Desiderata for Representation Learning from Identifiability, Disentanglement, and Group-Structuredness 2nd Annual Topology, Algebra, and Geometry in Machine Learning (TAG) at ICML 2023, July 2023 (conference)

link (url) [BibTex]

Reizinger, P., Sharma, Y., Bethge, M., Schölkopf, B., Huszár, F., Brendel, W. Jacobian-based Causal Discovery with Nonlinear ICA Transactions on Machine Learning Research, April 2023 (article)

link (url) [BibTex]

Reizinger*, P., Gresele*, L., Brady*, J., von Kügelgen, J., Zietlow, D., Schölkopf, B., Martius, G., Brendel, W., Besserve, M. Embrace the Gap: VAEs Perform Independent Mechanism Analysis Advances in Neural Information Processing Systems (NeurIPS 2022), 35, pages: 12040-12057, (Editors: S. Koyejo and S. Mohamed and A. Agarwal and D. Belgrave and K. Cho and A. Oh), Curran Associates, Inc., 36th Annual Conference on Neural Information Processing Systems, December 2022, *equal first authorship (conference)

Arxiv PDF link (url) [BibTex]

Zimmermann, Roland S, Brendel, Wieland, Tramer, Florian, Carlini, Nicholas Increasing Confidence in Adversarial Robustness Evaluations arXiv preprint arXiv:2206.13991, 2022 (article)

[BibTex]

Reizinger, Patrik, Gresele, Luigi, Brady, Jack, von Kügelgen, Julius, Zietlow, Dominik, Schölkopf, Bernhard, Martius, Georg, Brendel, Wieland, Besserve, Michel Embrace the Gap: VAEs Perform Independent Mechanism Analysis arXiv preprint arXiv:2206.02416, 2022 (article)

[BibTex]

Rusak, Evgenia, Schneider, Steffen, Gehler, Peter Vincent, Bringmann, Oliver, Brendel, Wieland, Bethge, Matthias ImageNet-D: A new challenging robustness dataset inspired by domain adaptation In ICML 2022 Shift Happens Workshop, 2022 (inproceedings)

[BibTex]

Li, Zhe, Caro, Josue Ortega, Rusak, Evgenia, Brendel, Wieland, Bethge, Matthias, Anselmi, Fabio, Patel, Ankit B, Tolias, Andreas S, Pitkow, Xaq Robust deep learning object recognition models rely on low frequency information in natural images bioRxiv, Cold Spring Harbor Laboratory, 2022 (article)

[BibTex]

Schott, Lukas, von Kügelgen, Julius, Träuble, Frederik, Gehler, Peter, Russell, Chris, Bethge, Matthias, Schölkopf, Bernhard, Locatello, Francesco, Brendel, Wieland Visual representation learning does not generalize strongly within the same domain In Tenth International Conference on Learning Representations (ICLR 2022), 2021 (inproceedings)

[BibTex]

Zimmermann, Roland S, Sharma, Yash, Schneider, Steffen, Bethge, Matthias, Brendel, Wieland Contrastive Learning Inverts the Data Generating Process In International Conference on Machine Learning (ICML 2021), 2021 (inproceedings)

[BibTex]

von Kügelgen, Julius, Sharma, Yash, Gresele, Luigi, Brendel, Wieland, Schölkopf, Bernhard, Besserve, Michel, Locatello, Francesco Self-Supervised Learning with Data Augmentations Provably Isolates Content from Style In 35th Conference on Neural Information Processing Systems (NeurIPS), 2021 (inproceedings)

[BibTex]

Pintor, Maura, Roli, Fabio, Brendel, Wieland, Biggio, Battista Fast Minimum-norm Adversarial Attacks through Adaptive Norm Constraints In 35th Conference on Neural Information Processing Systems (NeurIPS), 2021 (inproceedings)

[BibTex]

Geirhos, Robert, Narayanappa, Kantharaju, Mitzkus, Benjamin, Thieringer, Tizian, Bethge, Matthias, Wichmann, Felix A, Brendel, Wieland Partial success in closing the gap between human and machine vision In 35th Conference on Neural Information Processing Systems (NeurIPS), 2021 (inproceedings)

[BibTex]

Funke, Christina M, Borowski, Judy, Stosio, Karolina, Brendel, Wieland, Wallis, Thomas SA, Bethge, Matthias Five points to check when comparing visual perception in humans and machines Journal of Vision, 21(3):16-16, The Association for Research in Vision and Ophthalmology, 2021 (article)

[BibTex]

Zimmermann, Roland S, Borowski, Judy, Geirhos, Robert, Bethge, Matthias, Wallis, Thomas SA, Brendel, Wieland How Well do Feature Visualizations Support Causal Understanding of CNN Activations? In 35th Conference on Neural Information Processing Systems (NeurIPS), 2021 (inproceedings)

[BibTex]

Rusak, Evgenia, Schneider, Steffen, Pachitariu, George, Eck, Luisa, Gehler, Peter Vincent, Bringmann, Oliver, Brendel, Wieland, Bethge, Matthias If your data distribution shifts, use self-learning 2021 (article)

[BibTex]

Rusak, Evgenia, Schneider, Steffen, Gehler, Peter, Bringmann, Oliver, Brendel, Wieland, Bethge, Matthias Adapting ImageNet-scale models to complex distribution shifts with self-learning arXiv preprint arXiv:2104.12928, 2021 (article)

[BibTex]

Klindt, David, Schott, Lukas, Sharma, Yash, Ustyuzhaninov, Ivan, Brendel, Wieland, Bethge, Matthias, Paiton, Dylan Towards Nonlinear Disentanglement in Natural Data with Temporal Sparse Coding In International Conference on Learning Representations (ICLR), 2020 (inproceedings)

[BibTex]

Borowski, Judy, Zimmermann, Roland S, Schepers, Judith, Geirhos, Robert, Wallis, Thomas SA, Bethge, Matthias, Brendel, Wieland Exemplary Natural Images Explain CNN Activations Better than Feature Visualizations In International Conference on Learning Representations (ICLR 2021), 2020 (inproceedings)

[BibTex]

Schneider123, Steffen, Krishna, Shubham, Eck, Luisa, Brendel, Wieland, Mathis, Mackenzie W, Bethge, Matthias Generalized Invariant Risk Minimization: relating adaptation and invariant representation learning 2020 (article)

[BibTex]

Brendel, Wieland, Bourdoukan, Ralph, Vertechi, Pietro, Machens, Christian K, Denéve, Sophie Learning to represent signals spike by spike PLoS computational biology, 16(3):e1007692, Public Library of Science San Francisco, CA USA, 2020 (article)

[BibTex]

Tramer, Florian, Carlini, Nicholas, Brendel, Wieland, Madry, Aleksander On adaptive attacks to adversarial example defenses In 34th Conference on Neural Information Processing Systems (NeurIPS), 2020 (inproceedings)

[BibTex]

Rauber, Jonas, Bethge, Matthias, Brendel, Wieland EagerPy: Writing code that works natively with PyTorch, TensorFlow, JAX, and NumPy arXiv preprint arXiv:2008.04175, 2020 (article)

[BibTex]

Ortega Caro, Josue, Ju, Yilong, Pyle, Ryan, Dey, Sourav, Brendel, Wieland, Anselmi, Fabio, Patel, Ankit Local Convolutions Cause an Implicit Bias towards High Frequency Adversarial Examples arXiv e-prints, pages: arXiv-2006, 2020 (article)

[BibTex]

Rusak, Evgenia, Schott, Lukas, Zimmermann, Roland, Bitterwolf, Julian, Bringmann, Oliver, Bethge, Matthias, Brendel, Wieland Increasing the robustness of DNNs against image corruptions by playing the Game of Noise In European Conference on Computer Vision (oral), 2020 (inproceedings)

[BibTex]

Geirhos, Robert, Jacobsen, Jörn-Henrik, Michaelis, Claudio, Zemel, Richard, Brendel, Wieland, Bethge, Matthias, Wichmann, Felix A Shortcut Learning in Deep Neural Networks Nature Machine Intelligence volume 2, pages665--673(2020), 2020 (article)

[BibTex]

Rusak, Evgenia, Schott, Lukas, Zimmermann, Roland S, Bitterwolf, Julian, Bringmann, Oliver, Bethge, Matthias, Brendel, Wieland A simple way to make neural networks robust against diverse image corruptions In European Conference on Computer Vision, pages: 53-69, 2020 (inproceedings)

[BibTex]

Caro, Josue Ortega, Ju, Yilong, Pyle, Ryan, Dey, Sourav, Brendel, Wieland, Anselmi, Fabio, Patel, Ankit Local convolutions cause an implicit bias towards high frequency adversarial examples arXiv preprint arXiv:2006.11440, 2020 (article)

[BibTex]

Weis, Marissa A, Chitta, Kashyap, Sharma, Yash, Brendel, Wieland, Bethge, Matthias, Geiger, Andreas, Ecker, Alexander S Unmasking the inductive biases of unsupervised object representations for video sequences Journal of Machine Learning Research (JMLR), 2020 (article)

[BibTex]

Rauber, Jonas, Zimmermann, Roland, Bethge, Matthias, Brendel, Wieland Foolbox native: Fast adversarial attacks to benchmark the robustness of machine learning models in pytorch, tensorflow, and jax Journal of Open Source Software, 5(53):2607, 2020 (article)

[BibTex]

Brendel, Wieland, Rauber, Jonas, Kurakin, Alexey, Papernot, Nicolas, Veliqi, Behar, Mohanty, Sharada P, Laurent, Florian, Salathé, Marcel, Bethge, Matthias, Yu, Yaodong, others Adversarial vision challenge The NeurIPS'18 Competition, pages: 129-153, Springer, Cham, 2020 (misc)

[BibTex]

Schneider, Steffen, Rusak, Evgenia, Eck, Luisa, Bringmann, Oliver, Brendel, Wieland, Bethge, Matthias Improving robustness against common corruptions by covariate shift adaptation In 34th Conference on Neural Information Processing Systems (NeurIPS), 2020 (inproceedings)

[BibTex]

Geirhos, Robert, Narayanappa, Kantharaju, Mitzkus, Benjamin, Bethge, Matthias, Wichmann, Felix A, Brendel, Wieland On the surprising similarities between supervised and self-supervised models In Shared Visual Representations in Humans & Machines Workshop (NeurIPS 2020), 2020 (inproceedings)

[BibTex]

Geirhos, Robert, Jacobsen, Jörn-Henrik, Michaelis, Claudio, Zemel, Richard, Brendel, Wieland, Bethge, Matthias, Wichmann, Felix A Unintended cue learning: Lessons for deep learning from experimental psychology In 20th Annual Meeting of the Vision Sciences Society (VSS 2020), 652-652, 2020 (inproceedings)

[BibTex]

Michaelis, Claudio, Mitzkus, Benjamin, Geirhos, Robert, Rusak, Evgenia, Bringmann, Oliver, Ecker, Alexander S, Bethge, Matthias, Brendel, Wieland Benchmarking robustness in object detection: Autonomous driving when winter is coming In NeurIPS 2019 Workshop on Machine Learning for Autonomous Driving, 2019 (inproceedings)

[BibTex]

Li, Zhe, Brendel, Wieland, Walker, Edgar, Cobos, Erick, Muhammad, Taliah, Reimer, Jacob, Bethge, Matthias, Sinz, Fabian, Pitkow, Zachary, Tolias, Andreas Learning from brains how to regularize machines In 33rd Conference on Neural Information Processing Systems (NeurIPS), pages: 9525-9535, 2019 (inproceedings)

[BibTex]

Brendel, Wieland, Bethge, Matthias Approximating cnns with bag-of-local-features models works surprisingly well on imagenet In Seventh International Conference on Learning Representations (ICLR 2019), 2019 (inproceedings)

[BibTex]

Carlini, Nicholas, Athalye, Anish, Papernot, Nicolas, Brendel, Wieland, Rauber, Jonas, Tsipras, Dimitris, Goodfellow, Ian, Madry, Aleksander, Kurakin, Alexey On evaluating adversarial robustness arXiv preprint arXiv:1902.06705, 2019 (article)

[BibTex]

Brendel, Wieland, Rauber, Jonas, Kümmerer, Matthias, Ustyuzhaninov, Ivan, Bethge, Matthias Accurate, reliable and fast robustness evaluation In 33rd Conference on Neural Information Processing Systems (NeurIPS), pages: 12841-12851, 2019 (inproceedings)

[BibTex]

Geirhos, Robert, Rubisch, Patricia, Michaelis, Claudio, Bethge, Matthias, Wichmann, Felix A, Brendel, Wieland ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness In Seventh International Conference on Learning Representations (ICLR 2019), 2018 (inproceedings)

[BibTex]

Böttcher, Alexander, Brendel, Wieland, Englitz, Bernhard, Bethge, Matthias Trace your sources in large-scale data: one ring to find them all arXiv preprint arXiv:1803.08882, 2018 (article)

[BibTex]

Schott, Lukas, Rauber, Jonas, Bethge, Matthias, Brendel, Wieland Towards the first adversarially robust neural network model on MNIST In Seventh International Conference on Learning Representations (ICLR 2019), 2018 (inproceedings)

[BibTex]

Funke, Christina, Borowski, Judy, Wallis, Thomas, Brendel, Wieland, Ecker, Alexander, Bethge, Matthias Comparing the ability of humans and DNNs to recognise closed contours in cluttered images Journal of Vision, 18(10):800-800, The Association for Research in Vision and Ophthalmology, 2018 (article)

[BibTex]

Oladazimi, Maysam, Brendel, Wieland, Schwarz, Cornelius Biomechanical texture coding in rat whiskers Scientific reports, 8(1):1-12, Nature Publishing Group, 2018 (article)

[BibTex]

Ustyuzhaninov, Ivan, Michaelis, Claudio, Brendel, Wieland, Bethge, Matthias One-shot texture segmentation arXiv preprint arXiv:1807.02654, 2018 (article)

[BibTex]

Brendel, Wieland, Bethge, Matthias Comment on" Biologically inspired protection of deep networks from adversarial attacks" arXiv preprint arXiv:1704.01547, 2017 (article)

[BibTex]

Brendel, Wieland, Rauber, Jonas, Bethge, Matthias Decision-based adversarial attacks: Reliable attacks against black-box machine learning models In Sixth International Conference on Learning Representations (ICLR 2018), 2017 (inproceedings)

[BibTex]

Ustyuzhaninov, Ivan, Brendel, Wieland, Gatys, Leon A, Bethge, Matthias What does it take to generate natural textures? In International Conference on Learning Representations (ICLR), 2017 (inproceedings)

[BibTex]

Rauber, Jonas, Brendel, Wieland, Bethge, Matthias Foolbox v0. 8.0: A python toolbox to benchmark the robustness of machine learning models In Reliable Machine Learning in the Wild Workshop, 34th International Conference on Machine Learning (ICML), 5, 2017 (inproceedings)

[BibTex]