Matthias Bethge

Concept-Aware Batch Sampling Improves Language-Image Pretraining CVPR 2026 Isolating the Role of Temporal Information in Video Saliency: A Controlled Experimental Analysis WACV 2026 Great Models Think Alike and this Undermines AI Oversight ICML 2025 How to Merge Your Multimodal Models Over Time? CVPR 2025 Identifying latent state transitions in non-linear dynamical systems ICLR 2025 In Search of Forgotten Domain Generalization ICLR 2025 LLMs on the Line: Data Determines Loss-to-Loss Scaling Laws ICML 2025 Modeling Saliency Dataset Bias ICCV 2025 ONEBench to Test Them All: Sample-Level Benchmarking Over Open-Ended Capabilities ACL 2025 Testing the Limits of Fine-Tuning for Improving Visual Cognition in Vision Language Models ICML 2025 VGGSounder: Audio-Visual Evaluations for Foundation Models ICCV 2025 WikiBigEdit: Understanding the Limits of Lifelong Knowledge Editing in LLMs ICML 2025 Adaptation Odyssey in LLMs: Why Does Additional Pretraining Sometimes Fail to Improve? EMNLP 2024 A Practitioner's Guide to Real-World Continual Multimodal Pretraining NeurIPS 2024 CiteME: Can Language Models Accurately Cite Scientific Claims? NeurIPS 2024 Does CLIP’s generalization performance mainly stem from high train-test similarity? ICLR 2024 Efficient Lifelong Model Evaluation in an Era of Rapid Progress NeurIPS 2024 Most discriminative stimuli for functional cell type clustering ICLR 2024 No "Zero-Shot" Without Exponential Data: Pretraining Concept Frequency Determines Multimodal Model Performance NeurIPS 2024 Object segmentation from common fate: Motion energy processing enables human-like zero-shot generalization to random dot stimuli NeurIPS 2024 Provable Compositional Generalization for Object-Centric Learning ICLR 2024 The Entropy Enigma: Success and Failure of Entropy Minimization ICML 2024 Visual Data-Type Understanding does not emerge from scaling Vision-Language Models ICLR 2024 Compositional Generalization from First Principles NeurIPS 2023 Modulated Neural ODEs NeurIPS 2023 RDumb: A simple approach that questions our progress in continual test-time adaptation NeurIPS 2023 Unsupervised Object Learning via Common Fate CLeaR 2023 Visual Representation Learning Does Not Generalize Strongly Within the Same Domain ICLR 2022 Benchmarking Unsupervised Object Representations for Video Sequences JMLR 2021 Contrastive Learning Inverts the Data Generating Process ICML 2021 DeepGaze IIE: Calibrated Prediction in and Out-of-Domain for State-of-the-Art Saliency Modeling ICCV 2021 Exemplary Natural Images Explain CNN Activations Better than State-of-the-Art Feature Visualization ICLR 2021 How Well do Feature Visualizations Support Causal Understanding of CNN Activations? NeurIPS 2021 Partial success in closing the gap between human and machine vision NeurIPS 2021 Pretraining Boosts Out-of-Domain Robustness for Pose Estimation WACV 2021 Towards Nonlinear Disentanglement in Natural Data with Temporal Sparse Coding ICLR 2021 A Simple Way to Make Neural Networks Robust Against Diverse Image Corruptions ECCV 2020 Improving robustness against common corruptions by covariate shift adaptation NeurIPS 2020 Measuring the Importance of Temporal Features in Video Saliency ECCV 2020 Rotation-invariant clustering of neuronal responses in primary visual cortex ICLR 2020 System Identification with Biophysical Constraints: A Circuit Model of the Inner Retina NeurIPS 2020 Accurate, reliable and fast robustness evaluation NeurIPS 2019 Approximating CNNs with Bag-of-local-Features models works surprisingly well on ImageNet ICLR 2019 A rotation-equivariant convolutional neural network model of primary visual cortex ICLR 2019 Excessive Invariance Causes Adversarial Vulnerability ICLR 2019 ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness ICLR 2019 Learning from brains how to regularize machines NeurIPS 2019 Towards the first adversarially robust neural network model on MNIST ICLR 2019 Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Models ICLR 2018 Diverse feature visualizations reveal invariances in early layers of deep neural networks ECCV 2018 Generalisation in humans and deep neural networks NeurIPS 2018 One-Shot Segmentation in Clutter ICML 2018 Saliency Benchmarking Made Easy: Separating Models, Maps and Metrics ECCV 2018 Controlling Perceptual Factors in Neural Style Transfer CVPR 2017 Neural system identification for large populations separating “what” and “where” NeurIPS 2017 Understanding Low- and High-Level Contributions to Fixation Prediction ICCV 2017 Image Style Transfer Using Convolutional Neural Networks CVPR 2016 Data modeling with the elliptical gamma distribution AISTATS 2015 Generative Image Modeling Using Spatial LSTMs NeurIPS 2015 Texture Synthesis Using Convolutional Neural Networks NeurIPS 2015 Training sparse natural image models with a fast Gibbs sampler of an extended state space NeurIPS 2012 In All Likelihood, Deep Belief Is Not Enough JMLR 2011 Evaluating neuronal codes for inference using Fisher information NeurIPS 2010 -Nested Symmetric Distributions JMLR 2010 A joint maximum-entropy model for binary neural population patterns and continuous signals NeurIPS 2009 Bayesian estimation of orientation preference maps NeurIPS 2009 Hierarchical Modeling of Local Image Features through L_p-Nested Symmetric Distributions NeurIPS 2009 Neurometric function analysis of population codes NeurIPS 2009 The Conjoint Effect of Divisive Normalization and Orientation Selectivity on Redundancy Reduction NeurIPS 2008 Bayesian Inference for Spiking Neuron Models with a Sparsity Prior NeurIPS 2007 Near-Maximum Entropy Models for Binary Neural Representations of Natural Images NeurIPS 2007 Receptive Fields without Spike-Triggering NeurIPS 2007