Publications · Bethge Lab

2026

Moving Forward with Video Saliency: A New Dataset and Benchmark where Motion Matters

Susmit Agrawal, Rebecca Wanner, Juliane Verwiebe, Matthias Tangemann, Matthias Bethge, Matthias Kümmerer

arXiv 2026arXiv Data

Replay on Demand: An Emergent Curriculum for Balancing Adaptation and Forgetting in Continued Pretraining

Lukas Thede, Shengzhuang Chen, Stefan Winzeck, Matthias Bethge, Zeynep Akata, Jonathan Richard Schwarz

arXiv 2026arXiv

MedKIT: Evaluating Knowledge Integration and Generalization in Large Language Models

Lukas Thede, Yash Kumar Atri, David Chen, Danielle Bitterman, Matthias Bethge, Tom Hartvigsen, Zeynep Akata

arXiv 2026arXiv

Instrumental Monitor Evasion Emerges Under Ordinary Task Pressure

David Schmotz, Derck Prinzhorn, Luca Beurer-Kellner, Anselm Paulus, Ameya Prabhu, Maksym Andriushchenko

arXiv 2026arXiv

LLM Agents Can Easily Tamper With Their Own Traces

Jeremy Qin, David Schmotz, Derck Prinzhorn, Luca Beurer-Kellner, Ameya Prabhu, Maksym Andriushchenko

arXiv 2026arXiv

LAION-BVD: A 10-Million-Hour Open Video Dataset for Multimodal Pre-training

Andreas Hochlehnert, Marianna Nezhurina, Mehdi Cherti, Andrej Radonjic, Thaddäus Wiedemer, , Jenia Jitsev, Matthias Bethge

NeurIPS 2026arXiv

Stealing Reasoning Traces from Proprietary LLM APIs

Alexander Panfilov, David Schmotz, Ilia Shumailov, Luca Beurer-Kellner, Joachim Schaeffer, Ameya Prabhu, Jonas Geiping, Maksym Andriushchenko

arXiv 2026arXiv

DeepGaze3.5-VL: Modeling Scanpaths via Autoregressive Token Prediction

Susmit Agrawal, Matthias Bethge, Matthias Kümmerer

ECCV 2026arXiv

QVal: Cheaply Evaluating Dense Supervision Signals for Long-Horizon LLM Agents

Sergio Hernández-Gutiérrez, Matteo Merler, Ilze Amanda Auzina, Joschka Strüber, Ameya Prabhu, Matthias Bethge

NeurIPS 2026arXiv

DataComp-VLM: Improved Open Datasets for Vision-Language Models

Matteo Farina, Vishaal Udandarao, Thao Nguyen, Selim Kuzucu, Maximilian Böther, , Ludwig Schmidt, Nikhil Parthasarathy

NeurIPS 2026arXiv

Retinal circuits in silico: A review of modern retina models and a vision for their future

Thomas Zenkel, Federico D’Agostino, Matthias Bethge, Thomas Euler, Larissa Höfling

Vision Research 2026DOI

Natural tipping dynamics as catalysts of human cooperation

Wolfram Barfuß, Jonathan F. Donges, Matthias Bethge, Simon A. Levin

Ecological Economics 2026DOI

FutureSim: Replaying World Events to Evaluate Adaptive Agents

Shashwat Goel, Nikhil Chandak, Arvindh Arun, Ameya Prabhu, Steffen Staab, Moritz Hardt, Maksym Andriushchenko, Jonas Geiping

arXiv 2026arXiv

Only Brains Align with Brains: Cross-Region Alignment Patterns Expose Limits of Normative Models

Larissa Höfling, Matthias Tangemann, Lotta Piefke, Susanne Keller, Katrin Franke, Matthias Bethge

arXiv 2026arXiv

LongCoT: Benchmarking Long-Horizon Chain-of-Thought Reasoning

Sumeet Motwani, Daniel Nichols, Charles London, Peggy Li, Fabio Pizzati, , Bhavya Kailkhura, Christian Schroeder de Witt

arXiv 2026arXiv

Round-Trip Translation Reveals What Frontier Multilingual Benchmarks Miss

Ronald Skorobogat, Ameya Prabhu, Matthias Bethge

arXiv 2026arXiv

Personalizing Text-to-Image Generation to Individual Taste

Anne-Sofie Maerten, Juliane Verwiebe, Shyamgopal Karthik, Ameya Prabhu, Johan P. Wagemans, Matthias Bethge

arXiv 2026arXiv

PostTrainBench: Can LLM Agents Automate LLM Post-Training?

Ben Rank, Hardik Bhatnagar, Ameya Prabhu, Shira Eisenberg, Karina Nguyen, Matthias Bethge, Maksym Andriushchenko

ICML 2026arXiv

Isolating the Role of Temporal Information in Video Saliency: A Controlled Experimental Analysis

Peter El-Jiz, Matthias Kuemmerer, Matthias Tangemann, Matthias Bethge, Andreas Bartels, Michael M. Bannert

WACV 2026DOI

Position: Modular Memory is the Key to Continual Learning Agents

Vaggelis Dorovatas, Malte Schwerin, Andrew D. Bagdanov, Lucas Caccia, Antonio Carta, , Martin Mundt, Rahaf Aljundi

arXiv 2026arXiv

Intrinsic Credit Assignment for Long Horizon Interaction

Ilze Amanda Auzina, Joschka Strüber, Sergio Hernández-Gutiérrez, Shashwat Goel, Ameya Prabhu, Matthias Bethge

arXiv 2026arXiv

A benchmark of expert-level academic questions to assess AI capabilities

Long Phan, Alice Gatti, Ziwen Han, Nathaniel Li, Josephina Hu, , Alexandr Wang, Dan Hendrycks

Nature 2026arXiv

2025

Scaling Open-Ended Reasoning to Predict the Future

Nikhil Chandak, Shashwat Goel, Ameya Prabhu, Moritz Hardt, Jonas Geiping

ICML 2026arXiv

Solving Spatial Supersensing Without Spatial Supersensing

Vishaal Udandarao, Shyamgopal Karthik, Surabhi S Nath, Andreas Hochlehnert, Matthias Bethge, Ameya Prabhu

arXiv 2025arXiv

LLM generation novelty through the lens of semantic similarity

Philipp Davydov, Ameya Prabhu, Matthias Bethge, Elisa Nguyen, Seong Joon Oh

arXiv 2025arXiv

Mapping Post-Training Forgetting in Language Models at Scale

Jackson Harmon, Andreas Hochlehnert, Matthias Bethge, Ameya Prabhu

ICLR 2026arXiv

VGGSounder: Audio-Visual Evaluations for Foundation Models

Daniil Zverev, Thaddäus Wiedemer, Ameya Prabhu, Matthias Bethge, Wieland Brendel, A. Sophia Koepke

ICCV 2025arXiv

Adaptive Attacks on Trusted Monitors Subvert AI Control Protocols

Mikhail Terekhov, Alexander Panfilov, Daniil Dzenhaliou, Caglar Gulcehre, Maksym Andriushchenko, Ameya Prabhu, Jonas Geiping

arXiv 2025arXiv

Modeling Saliency Dataset Bias

Matthias Kuemmerer, Harneet Singh Khanuja, Matthias Bethge

ICCV 2025PDF Code

Strategic Dishonesty Can Undermine AI Safety Evaluations of Frontier LLMs

Panfilov, Alexander, Evgenii Kortukov, Kristina Nikolić, Matthias Bethge, Sebastian Lapuschkin, Wojciech Samek, Ameya Prabhu, Maksym Andriushchenko, Jonas Geiping

arXiv 2025arXiv

AlgoTune: Can Language Models Speed Up General-Purpose Numerical Programs?

Ori Press, Brandon Amos, Haoyu Zhao, Yikai Wu, Samuel K. Ainsworth, , Matthias Bethge, Ofir Press

NeurIPS 2025arXiv

Answer Matching Outperforms Multiple Choice for Language Model Evaluation

Nikhil Chandak, Shashwat Goel, Ameya Prabhu, Moritz Hardt, Jonas Geiping

arXiv 2025arXiv

A foundation model to predict and capture human cognition

Marcel Binz, Elif Akata, Matthias Bethge, Franziska Brändle, Fred Callaway, , Hua-Dong Xiong, Eric Schulz

Nature 2025PDF

A Good CREPE needs more than just Sugar: Investigating Biases in Compositional Vision-Language Benchmarks

Vishaal Udandarao, Mehdi Cherti, Shyamgopal Karthik, Jenia Jitsev, Samuel Albanie, Matthias Bethge

arXiv 2025arXiv

Playing repeated games with large language models

Elif Akata, Lion Schulz, Julian Coda-Forno, Seong Joon Oh, Matthias Bethge, Eric Schulz

Nature Human Behaviour 2025arXiv

A Sober Look at Progress in Language Model Reasoning: Pitfalls and Paths to Reproducibility

Andreas Hochlehnert, Hardik Bhatnagar, Vishaal Udandarao, Samuel Albanie, Ameya Prabhu, Matthias Bethge

COLM 2025arXiv

Are We Done with Object-Centric Learning?

Alexander Rubinstein, Ameya Prabhu, Matthias Bethge, Oh, Seong Joon

arXiv 2025arXiv

The openretina Project: Collaborative Retina Modelling Across Datasets and Species

Federico D’Agostino, Thomas Zenkel, Baptiste Lorenzi, Michaela Vystrčilová, Dominic Gonschorek, , Thomas Euler, Matthias Bethge

eLife 2025PDF

WikiBigEdit: Understanding the Limits of Lifelong Knowledge Editing in LLMs

Lukas Thede, Karsten Roth, Matthias Bethge, Zeynep Akata, Hartvigsen, Tom

ICML 2025arXiv

Can Language Models Falsify? Evaluating Algorithmic Reasoning with Counterexample Creation

Shiven Sinha, Shashwat Goel, Ponnurangam Kumaraguru, Jonas Geiping, Matthias Bethge, Ameya Prabhu

arXiv 2025arXiv

LLMs on the Line: Data Determines Loss-to-Loss Scaling Laws

Prasanna Mayilvahanan, Thaddäus Wiedemer, Sayak Mallick, Matthias Bethge, Wieland Brendel

ICML 2025PDF arXiv Code Project

Pretraining Frequency Predicts Compositional Generalization of CLIP on Real-World Tasks

Thaddäus Wiedemer, Yash Sharma, Ameya Prabhu, Matthias Bethge, Wieland Brendel

arXiv 2025PDF

Great Models Think Alike and this Undermines AI Oversight

Shashwat Goel, Joschka Strüber, Ilze Amanda Auzina, Karuna K Chandra, Ponnurangam Kumaraguru, Douwe Kiela, Ameya Prabhu, Matthias Bethge, Jonas Geiping

ICML 2025arXiv

Open Problems in Machine Unlearning for AI Safety

Fazl Barez, Tingchen Fu, Ameya Prabhu, Casper, Stephen, Amartya Sanyal, , Mor Geva, Yarin Gal

arXiv 2025arXiv

Project Alexandria: Towards Freeing Scientific Knowledge from Copyright Burdens via LLMs

Christoph G. Schuhmann, Gollam Rabby, Ameya Prabhu, Ahmed, Tawsif, Andreas Hochlehnert, , Jenia Jitsev, Matthias Bethge

arXiv 2025arXiv

2024

How to Merge Your Multimodal Models Over Time?

Sebastian Dziadzio, Vishaal Udandarao, Karsten Roth, Ameya Prabhu, Zeynep Akata, Samuel Albanie, Matthias Bethge

CVPR 2025PDF Code

ONEBench to Test Them All: Sample-Level Benchmarking Over Open-Ended Capabilities

Adhiraj Ghosh, Sebastian Dziadzio, Ameya Prabhu, Vishaal Udandarao, Samuel Albanie, Matthias Bethge

ACL 2025PDF arXiv

Reflecting on the State of Rehearsal-free Continual Learning with Pretrained Models

Lukas Thede, Karsten Roth, Olivier J. Henaff, Matthias Bethge, Zeynep Akata

CoLLAs 2024PDF

RDumb: A simple approach that questions our progress in continual test-time adaptation

Ori Press, Steffen Schneider, Matthias Kuemmerer, Matthias Bethge

NeurIPS 2023PDF Code

The Entropy Enigma: Success and Failure of Entropy Minimization

Ori Press, Ravid Shwartz-Ziv, Yann LeCun, Matthias Bethge

ICML 2024PDF Code

Infinite dSprites for Disentangled Continual Learning: Separating Memory Edits from Generalization

Sebastian Dziadzio, Çağatay Yıldız, Gido M. van de Ven, Tomasz Trzciński, Tinne Tuytelaars, Matthias Bethge

CoLLAs 2024PDF Code Project Data

A chromatic feature detector in the retina signals visual context changes

Larissa Hoefling, Klaudia P Szatko, Christian Behrens, Yuyao Deng, Yongrong Qiu, , Alexander S Ecker, Thomas Euler

eLife 2024PDF

In Search of Forgotten Domain Generalization

Prasanna Mayilvahanan, Roland Zimmermann, Thaddäus Wiedemer, Evgenia Rusak, Attila Juhos, Matthias Bethge, Wieland Brendel

ICLR 2025PDF

Adaptation Odyssey in LLMs: Why Does Additional Pretraining Sometimes Fail to Improve?

Fırat Öncel, Matthias Bethge, Beyza Ermis, Mirco Ravanelli, Cem Subakan, Çağatay Yıldız

EMNLP 2024PDF

CiteME: Can Language Models Accurately Cite Scientific Claims?

Ori Press, Andreas Hochlehnert, Ameya Prabhu, Vishaal Udandarao, Ofir Press, Matthias Bethge

NeurIPS 2024PDF Code Project

Efficient Lifelong Model Evaluation in an Era of Rapid Progress

Ameya Prabhu, Vishaal Udandarao, Philip Torr, Matthias Bethge, Adel Bibi, Samuel Albanie

NeurIPS 2024PDF Code Data

No Zero-Shot Without Exponential Data---Pretraining Concept Frequency Determines Multimodal Model Performance

Vishaal Udandarao, Ameya Prabhu, Adhiraj Ghosh, Yash Sharma, Philip Torr, Adel Bibi, Samuel Albanie, Matthias Bethge

NeurIPS 2024PDF Code Data

SuS-X---Training-Free Name-Only Transfer of Vision-Language Models

Vishaal Udandarao, Ankush Gupta, Samuel Albanie

ICCV 2023PDF Code

Visual Data-Type Understanding does not emerge from Scaling Vision-Language Models

Vishaal Udandarao, Max F. Burg, Samuel Albanie, Matthias Bethge

ICLR 2024PDF Code Data

Future views on neuroscience and AI

Ilana B. Witten, Daniel L. K. Yamins, Claudia Clopath, Matthias Bethge, Yi Zeng, Ann R. Kennedy, Abeba Birhane, Doris Y. Tsao, Been Kim, Ila Fiete

Cell 2024DOI

Object segmentation from common fate: Motion energy processing enables human-like zero-shot generalization to random dot stimuli

Matthias Tangemann, Matthias Kuemmerer, Matthias Bethge

NeurIPS 2024

Identifying latent state transition in non-linear dynamical systems

Çağlar Hızlı, Çağatay Yıldız, Matthias Bethge, ST John, Pekka Marttinen

arXiv 2024PDF

Potsdam data set of eye movement on natural scenes (DAEMONS)

Lisa Schwetlick, Matthias Kümmerer, Matthias Bethge, Ralf Engbert

Frontiers in Psychology 2024PDF

Wu's Method can Boost Symbolic AI to Rival Silver Medalists and AlphaGeometry to Outperform Gold Medalists at IMO Geometry

Shiven Sinha, Ameya Prabhu, Ponnurangam Kumaraguru, Siddharth Bhat, Matthias Bethge

arXiv 2024arXiv

Scale Learning in Scale-Equivariant Convolutional Networks

Mark Basting, Robert-Jan Bruintjes, Thaddäus Wiedemer, Matthias Kümmerer, Matthias Bethge, Jan van Gemert

VISAPP 2024PDF

Ecologically-mediated collective action in commons with tipping elements

Wolfram Barfuß, Jonathan F. Donges, Matthias Bethge

PDF

Investigating Continual Pretraining in Large Language Models: Insights and Implications

Çağatay Yıldız, Nishaanth Kanna Ravichandran, Matthias Bethge, Beyza Ermis

arXiv 2024PDF

A Practitioner's Guide to Real-World Continual Multimodal Pretraining

Vishaal Udandarao, Karsten Roth, Sebastian Dziadzio, Ameya Prabhu, Mehdi Cherti, Oriol Vinyals, Olivier J. Hénaff, Samuel Albanie, Zeynep Akata, Matthias Bethge

NeurIPS 2024DOI

2023

Modulated Neural ODEs

Ilze Amanda Auzina, Çağatay Yıldız, Sara Magliacane, Matthias Bethge, Efstratios Gavves

NeurIPS 2023PDF Code

Most discriminative stimuli for functional cell type clustering

Max F. Burg, Thomas Zenkel, Michaela Vystrčilová, Jonathan Oesterle, Larissa Höfling, , Matthias Bethge, Alexander S. Ecker

ICLR 2024arXiv

Visual cognition in multimodal large language models

Luca M. Schulze Buschoff, Elif Akata, Matthias Bethge, Eric Schulz

Nature Machine Intelligence 2025arXiv

Continual Learning: Applications and the Road Forward

Eli Verwimp, Rahaf Aljundi, Shai Ben-David, Matthias Bethge, Andrea Cossu, , Tinne Tuytelaars, Gido M. van de Ven

TMLR 2024arXiv

Does CLIP's Generalization Performance Mainly Stem from High Train-Test Similarity?

Prasanna Mayilvahanan, Thaddäus Wiedemer, Evgenia Rusak, Matthias Bethge, Wieland Brendel

ICLR 2024PDF Code Project

Provable Compositional Generalization for Object-Centric Learning

Thaddäus Wiedemer, Jack Brady, Alexander Panfilov, Attila Juhos, Matthias Bethge, Wieland Brendel

ICLR 2024PDF Code Project

Compositional Generalization from First Principles

Thaddäus Wiedemer, Prasanna Mayilvahanan, Matthias Bethge, Wieland Brendel

NeurIPS 2023PDF Code

Unsupervised object learning via common fate

Matthias Tangemann, Steffen Schneider, Julius Von Kügelgen, Francesco Locatello, Peter Gehler, Thomas Brox, Matthias Kuemmerer, Matthias Bethge, Bernhard Schölkopf

CLeaR 2023PDF Code

2022

Disentanglement and generalization under correlation shifts

Christina M Funke, Paul Vicol, Kuan-Chieh Wang, Matthias Kuemmerer, Richard Zemel, Matthias Bethge

CoLLAs 2022PDF

Deepgaze iii: Modeling free-viewing human scanpaths with deep learning

Matthias Kuemmerer, Matthias Bethge, Thomas SA Wallis

Journal of Vision 2022PDF

Digital twin reveals combinatorial code of non-linear computations in the mouse primary visual cortex

Ivan Ustyuzhaninov, Max F Burg, Santiago A Cadena, Jiakun Fu, Taliah Muhammad, , Andreas S Tolias, Alexander S Ecker

bioRxiv 2022PDF

Robust deep learning object recognition models rely on low frequency information in natural images

Zhe Li, Josue Ortega Caro, Evgenia Rusak, Wieland Brendel, Matthias Bethge, Fabio Anselmi, Ankit B Patel, Andreas S Tolias, Xaq Pitkow

PLOS Computational Biology 2023PDF

Semantic object-scene inconsistencies affect eye movements, but not in the way predicted by contextualized meaning maps

MA Pedziwiatr, Matthias Kümmerer, Thomas SA Wallis, M Bethge, C Teufel

Journal of Vision 2022PDF

Efficient coding of natural scenes improves neural system identification

Yongrong Qiu, David A Klindt, Klaudia P Szatko, Dominic Gonschorek, Larissa Hoefling, Timm Schubert, Laura Busse, Matthias Bethge, Thomas Euler

PLOS Computational Biology 2023PDF

Diverse task-driven modeling of macaque V4 reveals functional specialization towards semantic tasks

Santiago A Cadena, Konstantin F Willeke, Kelli Restivo, George Denfield, Fabian H Sinz, Matthias Bethge, Andreas S Tolias, Alexander S Ecker

PLOS Computational Biology 2024PDF

ImageNet-D: A new challenging robustness dataset inspired by domain adaptation

Evgenia Rusak, Steffen Schneider, Peter Vincent Gehler, Oliver Bringmann, Wieland Brendel, Matthias Bethge

PDF

2021

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

Roland S Zimmermann, Judy Borowski, Robert Geirhos, Matthias Bethge, Thomas Wallis, Wieland Brendel

NeurIPS 2021PDF

Partial success in closing the gap between human and machine vision

Robert Geirhos, Kantharaju Narayanappa, Benjamin Mitzkus, Tizian Thieringer, Matthias Bethge, Felix A Wichmann, Wieland Brendel

NeurIPS 2021PDF

Contextualised meaning maps do not predict how semantic object-context inconsistencies change human gaze behaviour

Marek A Pedziwiatr, Matthias Kuemmerer, Thomas SA Wallis, Matthias Bethge, Christoph Teufel

PDF

If your data distribution shifts, use self-learning

Evgenia Rusak, Steffen Schneider, George Pachitariu, Luisa Eck, Peter Vincent Gehler, Oliver Bringmann, Wieland Brendel, Matthias Bethge

TMLR 2022PDF

There is no evidence that meaning maps capture semantic information relevant to gaze guidance: Reply to Henderson, Hayes, Peacock, and Rehrig (2021)

Marek A Pedziwiatr, Matthias Kuemmerer, Thomas SA Wallis, Matthias Bethge, Christoph Teufel

Cognition 2021PDF

Visual representation learning does not generalize strongly within the same domain

Lukas Schott, Julius Von Kügelgen, Frederik Träuble, Peter Gehler, Chris Russell, Matthias Bethge, Bernhard Schölkopf, Francesco Locatello, Wieland Brendel

ICLR 2022PDF

Contrastive learning inverts the data generating process

Roland S Zimmermann, Yash Sharma, Steffen Schneider, Matthias Bethge, Wieland Brendel

ICML 2021PDF

Learning divisive normalization in primary visual cortex

Max F Burg, Santiago A Cadena, George H Denfield, Edgar Y Walker, Andreas S Tolias, Matthias Bethge, Alexander S Ecker

PLOS Computational Biology 2021PDF

Five points to check when comparing visual perception in humans and machines

Christina M Funke, Judy Borowski, Karolina Stosio, Wieland Brendel, Thomas SA Wallis, Matthias Bethge

Journal of Vision 2021PDF

State-of-the-art in human scanpath prediction

Matthias Kuemmerer, Matthias Bethge

arXiv 2021PDF

A diverse task-driven characterization of early and mid-level representations of the primate ventral stream

Santiago A Cadena, K Willeke, K Restivo, G Denfield, EY Walker, Fabian H Sinz, M Bethge, AS Tolias, Alexander S Ecker

PDF

Benchmarking unsupervised object representations for video sequences

Marissa A Weis, Kashyap Chitta, Yash Sharma, Wieland Brendel, Matthias Bethge, Andreas Geiger, Alexander S Ecker

JMLR 2021PDF

DeepGaze IIE: Calibrated prediction in and out-of-domain for state-of-the-art saliency modeling

Akis Linardos, Matthias Kuemmerer, Ori Press, Matthias Bethge

ICCV 2021PDF

Meaning maps and saliency models based on deep convolutional neural networks are insensitive to image meaning when predicting human fixations

Marek A Pedziwiatr, Matthias Kuemmerer, Thomas SA Wallis, Matthias Bethge, Christoph Teufel

Cognition 2021PDF

Out-of-distribution generalization of internal models is correlated with reward

Khushdeep Singh Mann, Steffen Schneider, Alberto Chiappa, Jin Hwa Lee, Matthias Bethge, Alexander Mathis, Mackenzie W Mathis

PDF

Pretraining boosts out-of-domain robustness for pose estimation

Alexander Mathis, Thomas Biasi, Steffen Schneider, Mert Yuksekgonul, Byron Rogers, Matthias Bethge, Mackenzie W Mathis

WACV 2021PDF

2020

Closing the generalization gap in one-shot object detection

Claudio Michaelis, Matthias Bethge, Alexander S Ecker

PDF

Shortcut learning in deep neural networks

Robert Geirhos, Jörn-Henrik Jacobsen, Claudio Michaelis, Richard Zemel, Wieland Brendel, Matthias Bethge, Felix A Wichmann

Nature Machine Intelligence 2020PDF

Exemplary natural images explain CNN activations better than state-of-the-art feature visualization

Judy Borowski, Roland S Zimmermann, Judith Schepers, Robert Geirhos, Thomas SA Wallis, Matthias Bethge, Wieland Brendel

arXiv 2020PDF

Foolbox native: Fast adversarial attacks to benchmark the robustness of machine learning models in pytorch, tensorflow, and jax

Jonas Rauber, Roland Zimmermann, Matthias Bethge, Wieland Brendel

Journal of Open Source Software 2020PDF

A 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

ECCV 2020PDF

EagerPy: Writing code that works natively with PyTorch, TensorFlow, JAX, and NumPy

Jonas Rauber, Matthias Bethge, Wieland Brendel

arXiv 2020PDF

Measuring the importance of temporal features in video saliency

Matthias Tangemann, Matthias Kuemmerer, Thomas SA Wallis, Matthias Bethge

ECCV 2020PDF Code

Towards nonlinear disentanglement in natural data with temporal sparse coding

David Klindt, Lukas Schott, Yash Sharma, Ivan Ustyuzhaninov, Wieland Brendel, Matthias Bethge, Dylan Paiton

ICLR 2021PDF

Imagenet performance correlates with pose estimation robustness and generalization on out-of-domain data

Alexander Mathis, Thomas Biasi, Y Mert, Byron Rogers, Matthias Bethge, Mackenzie Weygandt Mathis

PDF

Unmasking the inductive biases of unsupervised object representations for video sequences

Marissa A Weis, Kashyap Chitta, Yash Sharma, Wieland Brendel, Matthias Bethge, Andreas Geiger, Alexander S Ecker

PDF

Task-driven hierarchical deep neural network models of the proprioceptive pathway

Kai J Sandbrink, Pranav Mamidanna, Claudio Michaelis, Mackenzie Weygandt Mathis, Matthias Bethge, Alexander Mathis

bioRxiv 2020PDF

Towards causal generative scene models via competition of experts

Julius von Kügelgen, Ivan Ustyuzhaninov, Peter Gehler, Matthias Bethge, Bernhard Schölkopf

arXiv 2020PDF

The temporal structure of the inner retina at a single glance

Zhijian Zhao, David A Klindt, André Maia Chagas, Klaudia P Szatko, Luke Rogerson, , Alexander S Ecker, Thomas Euler

Scientific Reports 2020PDF

Adversarial vision challenge

Wieland Brendel, Jonas Rauber, Alexey Kurakin, Nicolas Papernot, Behar Veliqi, , Wenshuo Li, Yu Wang

The NeurIPS '18 Competition (Springer) 2020PDF

Generalized Invariant Risk Minimization: relating adaptation and invariant representation learning

Steffen Schneider123, Shubham Krishna, Luisa Eck, Wieland Brendel, Mackenzie W Mathis, Matthias Bethge

PDF

Improving robustness against common corruptions by covariate shift adaptation

Steffen Schneider, Evgenia Rusak, Luisa Eck, Oliver Bringmann, Wieland Brendel, Matthias Bethge

NeurIPS 2020PDF

Natural images are more informative for interpreting cnn activations than state-of-the-art synthetic feature visualizations

Judy Borowski, Roland Simon Zimmermann, Judith Schepers, Robert Geirhos, Thomas SA Wallis, Matthias Bethge, Wieland Brendel

PDF

Rotation-invariant clustering of neuronal responses in primary visual cortex

Ivan Ustyuzhaninov, Santiago A Cadena, Emmanouil Froudarakis, Paul G Fahey, Edgar Y Walker, , Matthias Bethge, Alexander S Ecker

ICLR 2020PDF

System identification with biophysical constraints: A circuit model of the inner retina

Cornelius Schröder, David Klindt, Sarah Strauss, Katrin Franke, Matthias Bethge, Thomas Euler, Philipp Berens

NeurIPS 2020PDF

2019

Engineering a less artificial intelligence

Fabian H Sinz, Xaq Pitkow, Jacob Reimer, Matthias Bethge, Andreas S Tolias

Neuron 2019PDF

How well do deep neural networks trained on object recognition characterize the mouse visual system?

Santiago A Cadena, Fabian H Sinz, Taliah Muhammad, Emmanouil Froudarakis, Erick Cobos, Edgar Y Walker, Jake Reimer, Matthias Bethge, Andreas Tolias, Alexander S Ecker

PDF

Benchmarking robustness in object detection: Autonomous driving when winter is coming

Claudio Michaelis, Benjamin Mitzkus, Robert Geirhos, Evgenia Rusak, Oliver Bringmann, Alexander S Ecker, Matthias Bethge, Wieland Brendel

arXiv 2019PDF

Using DeepLabCut for 3D markerless pose estimation across species and behaviors

Tanmay Nath, Alexander Mathis, An Chi Chen, Amir Patel, Matthias Bethge, Mackenzie Weygandt Mathis

Nature Protocols 2019PDF

Image content is more important than Bouma’s Law for scene metamers

Thomas SA Wallis, Christina M Funke, Alexander S Ecker, Leon A Gatys, Felix A Wichmann, Matthias Bethge

eLife 2019PDF

Deep convolutional models improve predictions of macaque V1 responses to natural images

Santiago A Cadena, George H Denfield, Edgar Y Walker, Leon A Gatys, Andreas S Tolias, Matthias Bethge, Alexander S Ecker

PLOS Computational Biology 2019PDF

Comparing Humans and Deep Neural Networks on Visual Shape Judgments in Cluttered Images

Christina Funke, Thomas Wallis, Judith Borowski, Claudio Michaelis, Alexander Ecker, Matthias Bethge

PDF

Probing Neural Decision-Making in Behavioral Models of Scanpath Prediction

Matthias Kuemmerer, Thomas Wallis, Matthias Bethge

PDF

Reproducing Decision-Making With Constrained Networks to Understand Deep Neural Networks

Judith Borowski, Wieland Brendel, Matthias Bethge

PDF

Approximating cnns with bag-of-local-features models works surprisingly well on imagenet

Wieland Brendel, Matthias Bethge

ICLR 2019PDF

Accurate, reliable and fast robustness evaluation

Wieland Brendel, Jonas Rauber, Matthias Kuemmerer, Ivan Ustyuzhaninov, Matthias Bethge

NeurIPS 2019PDF

Learning from brains how to regularize machines

Zhe Li, Wieland Brendel, Edgar Walker, Erick Cobos, Taliah Muhammad, Jacob Reimer, Matthias Bethge, Fabian Sinz, Zachary Pitkow, Andreas Tolias

NeurIPS 2019PDF

2018

ImageNet-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

ICLR 2019PDF

Excessive invariance causes adversarial vulnerability

Jörn-Henrik Jacobsen, Jens Behrmann, Richard Zemel, Matthias Bethge

ICLR 2019PDF

Faster processing of moving compared with flashed bars in awake macaque V1 provides a neural correlate of the flash lag illusion

Manivannan Subramaniyan, Alexander S Ecker, Saumil S Patel, R James Cotton, Matthias Bethge, Xaq Pitkow, Philipp Berens, Andreas S Tolias

Journal of Neurophysiology 2018PDF

A 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

ICLR 2019PDF

DeepLabCut: markerless pose estimation of user-defined body parts with deep learning

Alexander Mathis, Pranav Mamidanna, Kevin M Cury, Taiga Abe, Venkatesh N Murthy, Mackenzie Weygandt Mathis, Matthias Bethge

Nature Neuroscience 2018PDF

Attentional fluctuations induce shared variability in macaque primary visual cortex

George H Denfield, Alexander S Ecker, Tori J Shinn, Matthias Bethge, Andreas S Tolias

Nature Communications 2018PDF

One-shot segmentation in clutter

Claudio Michaelis, Matthias Bethge, Alexander Ecker

ICML 2018PDF

Towards the first adversarially robust neural network model on MNIST

Lukas Schott, Jonas Rauber, Matthias Bethge, Wieland Brendel

ICLR 2019PDF

Community-based benchmarking improves spike rate inference from two-photon calcium imaging data

Philipp Berens, Jeremy Freeman, Thomas Deneux, Nikolay Chenkov, Thomas McColgan, , Andreas S Tolias, Matthias Bethge

PLOS Computational Biology 2018PDF

Trace your sources in large-scale data: one ring to find them all

Alexander Böttcher, Wieland Brendel, Bernhard Englitz, Matthias Bethge

arXiv 2018PDF

Diverse 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

ECCV 2018PDF

Generalisation in humans and deep neural networks

Robert Geirhos, Carlos RM Temme, Jonas Rauber, Heiko H Schütt, Matthias Bethge, Felix A Wichmann

NeurIPS 2018PDF

Introduction to NIPS 2017 Competition Track

Sergio Escalera, Markus Weimer, Mikhail Burtsev, Valentin Malykh, Varvara Logacheva, , Ian Goodfellow, Samy Bengio

The NIPS '17 Competition (Springer) 2018PDF

Multi-task generalization and adaptation between noisy digit datasets: An empirical study

Steffen Schneider, Alexander S Ecker, Jakob H Macke, Matthias Bethge

PDF

Salad: A toolbox for semi-supervised adaptive learning across domains

Steffen Schneider, Alexander S Ecker, Jakob H Macke, Matthias Bethge

NeurIPS 2018 WorkshopPDF

Saliency benchmarking made easy: Separating models, maps and metrics

Matthias Kummerer, Thomas SA Wallis, Matthias Bethge

ECCV 2018PDF

2017

Guiding human gaze with convolutional neural networks

Leon A Gatys, Matthias Kuemmerer, Thomas SA Wallis, Matthias Bethge

arXiv 2017PDF

Decision-based adversarial attacks: Reliable attacks against black-box machine learning models

Wieland Brendel, Jonas Rauber, Matthias Bethge

ICLR 2018PDF

Neural system identification for large populations separating what and where

David A Klindt, Alexander S Ecker, Thomas Euler, Matthias Bethge

NeurIPS 2017PDF

Signatures of criticality arise from random subsampling in simple population models

Marcel Nonnenmacher, Christian Behrens, Philipp Berens, Matthias Bethge, Jakob H Macke

PLOS Computational Biology 2017PDF

A parametric texture model based on deep convolutional features closely matches texture appearance for humans

Thomas SA Wallis, Christina M Funke, Alexander S Ecker, Leon A Gatys, Felix A Wichmann, Matthias Bethge

Journal of Vision 2017PDF

Texture and art with deep neural networks

Leon A Gatys, Alexander S Ecker, Matthias Bethge

Current Opinion in Neurobiology 2017PDF

Foolbox: A python toolbox to benchmark the robustness of machine learning models

Jonas Rauber, Wieland Brendel, Matthias Bethge

arXiv 2017PDF

Comparing deep neural networks against humans: object recognition when the signal gets weaker

Robert Geirhos, David HJ Janssen, Heiko H Schütt, Jonas Rauber, Matthias Bethge, Felix A Wichmann

arXiv 2017PDF

Comment on" Biologically inspired protection of deep networks from adversarial attacks

Wieland Brendel, Matthias Bethge

arXiv 2017PDF

Detecting distortions of peripherally presented letter stimuli under crowded conditions

Thomas S A. Wallis, Saskia Tobias, Matthias Bethge, Felix A Wichmann

Attention, Perception, & Psychophysics 2017PDF

Inhibition decorrelates visual feature representations in the inner retina

Katrin Franke, Philipp Berens, Timm Schubert, Matthias Bethge, Thomas Euler, Tom Baden

Nature 2017PDF

Synthesising dynamic textures using convolutional neural networks

Christina M Funke, Leon A Gatys, Alexander S Ecker, Matthias Bethge

arXiv 2017PDF

Boosting olfactory cocktail-party performance by semi-supervised learning in mice

Alexander Mathis, A Wei, A Ding, M Bethge, VN Murthy

PDF

Methods and measurements to compare men against machines

Felix A Wichmann, David HJ Janssen, Robert Geirhos, Guillermo Aguilar, Heiko H Schütt, Marianne Maertens, Matthias Bethge

Electronic Imaging 2017PDF

Controlling perceptual factors in neural style transfer

Leon A Gatys, Alexander S Ecker, Matthias Bethge, Aaron Hertzmann, Eli Shechtman

CVPR 2017PDF

Die Retina im Rausch der Kanäle

K Franke, Philipp Berens, T Schubert, M Bethge, T Euler

Klinische Monatsblätter für Augenheilkunde 2017PDF

Understanding low-and high-level contributions to fixation prediction

Matthias Kummerer, Thomas SA Wallis, Leon A Gatys, Matthias Bethge

ICCV 2017PDF

2016

DeepGaze II: Reading fixations from deep features trained on object recognition

Matthias Kuemmerer, Thomas SA Wallis, Matthias Bethge

arXiv 2016PDF

Reading out olfactory receptors: feedforward circuits detect odors in mixtures without demixing

Alexander Mathis, Dan Rokni, Vikrant Kapoor, Matthias Bethge, Venkatesh N Murthy

Neuron 2016PDF

Inference and mixture modeling with the Elliptical Gamma Distribution

Reshad Hosseini, Suvrit Sra, Lucas Theis, Matthias Bethge

Computational Statistics & Data Analysis 2016PDF

Preserving color in neural artistic style transfer

Leon A Gatys, Matthias Bethge, Aaron Hertzmann, Eli Shechtman

arXiv 2016PDF

Texture synthesis using shallow convolutional networks with random filters

Ivan Ustyuzhaninov, Wieland Brendel, Leon A Gatys, Matthias Bethge

arXiv 2016PDF

Benchmarking spike rate inference in population calcium imaging

Lucas Theis, Philipp Berens, Emmanouil Froudarakis, Jacob Reimer, Miroslav Román Rosón, Tom Baden, Thomas Euler, Andreas S Tolias, Matthias Bethge

Neuron 2016PDF

On the structure of neuronal population activity under fluctuations in attentional state

Alexander S Ecker, George H Denfield, Matthias Bethge, Andreas S Tolias

Journal of Neuroscience 2016PDF

Electrophysiological, transcriptomic and morphologic profiling of single neurons using Patch-seq

Cathryn R Cadwell, Athanasia Palasantza, Xiaolong Jiang, Philipp Berens, Qiaolin Deng, , Rickard Sandberg, Andreas S Tolias

Nature Biotechnology 2016PDF

The functional diversity of retinal ganglion cells in the mouse

Tom Baden, Philipp Berens, Katrin Franke, Miroslav Román Rosón, Matthias Bethge, Thomas Euler

Nature 2016PDF

A goal-driven deep learning approach for V1 system identification

Santiago A Cadena, Alexander S Ecker, G Denfield, E Walker, A Tolias, M Bethge

PDF

Image style transfer using convolutional neural networks

Leon A Gatys, Alexander S Ecker, Matthias Bethge

CVPR 2016PDF

2015

Information-theoretic model comparison unifies saliency metrics

Matthias Kuemmerer, Thomas SA Wallis, Matthias Bethge

PNAS 2015PDF

A note on the evaluation of generative models

Lucas Theis, Aäron van den Oord, Matthias Bethge

ICLR 2016PDF

Modeling natural image statistics

Holly E Gerhard, Lucas Theis, Matthias Bethge

PDF

A neural algorithm of artistic style

Leon A Gatys, Alexander S Ecker, Matthias Bethge

arXiv 2015PDF

Synaptic unreliability facilitates information transmission in balanced cortical populations

Leon A Gatys, Alexander S Ecker, Tatjana Tchumatchenko, Matthias Bethge

Physical Review E 2015PDF

A generative model of natural texture surrogates

Niklas Ludtke, Debapriya Das, Lucas Theis, Matthias Bethge

arXiv 2015PDF

Data modeling with the elliptical gamma distribution

Suvrit Sra, Reshad Hosseini, Lucas Theis, Matthias Bethge

AISTATS 2015PDF

Generative image modeling using spatial lstms

Lucas Theis, Matthias Bethge

NeurIPS 2015PDF

Texture synthesis using convolutional neural networks

Leon Gatys, Alexander S Ecker, Matthias Bethge

NeurIPS 2015PDF

2014

Deep gaze i: Boosting saliency prediction with feature maps trained on imagenet

Matthias Kuemmerer, Lucas Theis, Matthias Bethge

ICLR 2015 WorkshopPDF

Natter: A Python Natural Image Statistics Toolbox

Fabian H Sinz, Jörn-Philipp Lies, Sebastian Gerwinn, Matthias Bethge

Journal of Statistical Software 2014PDF

Population code in mouse V1 facilitates readout of natural scenes through increased sparseness

Emmanouil Froudarakis, Philipp Berens, Alexander S Ecker, R James Cotton, Fabian H Sinz, Dimitri Yatsenko, Peter Saggau, Matthias Bethge, Andreas S Tolias

Nature Neuroscience 2014PDF

State dependence of noise correlations in macaque primary visual cortex

Alexander S Ecker, Philipp Berens, R James Cotton, Manivannan Subramaniyan, George H Denfield, Cathryn R Cadwell, Stelios M Smirnakis, Matthias Bethge, Andreas S Tolias

Neuron 2014PDF