Matthias Bethge

papers

1,376

total citations

papers (22)

Improving robustness against common corruptions by covariate shift adaptation

NEURIPS 2020arXiv

593

citations

Partial success in closing the gap between human and machine vision

NEURIPS 2021arXiv

267

citations

DeepGaze IIE: Calibrated Prediction in and Out-of-Domain for State-of-the-Art Saliency Modeling

ICCV 2021arXiv

citations

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

COLM 2025arXiv

citations

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

ECCV 2020arXiv

citations

Compositional Generalization from First Principles

NEURIPS 2023arXiv

citations

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

NEURIPS 2023arXiv

citations

Does CLIP’s generalization performance mainly stem from high train-test similarity?

ICLR 2024arXiv

citations

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

NEURIPS 2021arXiv

citations

Can Language Models Falsify? Evaluating Algorithmic Reasoning with Counterexample Creation

COLM 2025arXiv

citations

Testing the Limits of Fine-Tuning for Improving Visual Cognition in Vision Language Models

ICML 2025arXiv

citations

Modeling Saliency Dataset Bias

ICCV 2025arXiv

citations

System Identification with Biophysical Constraints: A Circuit Model of the Inner Retina

NEURIPS 2020

citations

Measuring the Importance of Temporal Features in Video Saliency

ECCV 2020

citations

Matthias Bethge

papers (22)

Improving robustness against common corruptions by covariate shift adaptation

Partial success in closing the gap between human and machine vision

DeepGaze IIE: Calibrated Prediction in and Out-of-Domain for State-of-the-Art Saliency Modeling

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

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

Compositional Generalization from First Principles

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

Does CLIP’s generalization performance mainly stem from high train-test similarity?

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

The Entropy Enigma: Success and Failure of Entropy Minimization

Great Models Think Alike and this Undermines AI Oversight

How to Merge Your Multimodal Models Over Time?

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

WikiBigEdit: Understanding the Limits of Lifelong Knowledge Editing in LLMs

Modulated Neural ODEs

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

VGGSounder: Audio-Visual Evaluations for Foundation Models

Can Language Models Falsify? Evaluating Algorithmic Reasoning with Counterexample Creation

Testing the Limits of Fine-Tuning for Improving Visual Cognition in Vision Language Models

Modeling Saliency Dataset Bias

System Identification with Biophysical Constraints: A Circuit Model of the Inner Retina

Measuring the Importance of Temporal Features in Video Saliency

papers (22)

Improving robustness against common corruptions by covariate shift adaptation

Partial success in closing the gap between human and machine vision

DeepGaze IIE: Calibrated Prediction in and Out-of-Domain for State-of-the-Art Saliency Modeling

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

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

Compositional Generalization from First Principles

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

Does CLIP’s generalization performance mainly stem from high train-test similarity?

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

The Entropy Enigma: Success and Failure of Entropy Minimization

Great Models Think Alike and this Undermines AI Oversight

How to Merge Your Multimodal Models Over Time?

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

WikiBigEdit: Understanding the Limits of Lifelong Knowledge Editing in LLMs

Modulated Neural ODEs

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

VGGSounder: Audio-Visual Evaluations for Foundation Models

Can Language Models Falsify? Evaluating Algorithmic Reasoning with Counterexample Creation

Testing the Limits of Fine-Tuning for Improving Visual Cognition in Vision Language Models

Modeling Saliency Dataset Bias

System Identification with Biophysical Constraints: A Circuit Model of the Inner Retina

Measuring the Importance of Temporal Features in Video Saliency