Alert button
Picture for Matthias Bethge

Matthias Bethge

Alert button

Playing repeated games with Large Language Models

May 26, 2023
Elif Akata, Lion Schulz, Julian Coda-Forno, Seong Joon Oh, Matthias Bethge, Eric Schulz

Figure 1 for Playing repeated games with Large Language Models
Figure 2 for Playing repeated games with Large Language Models
Figure 3 for Playing repeated games with Large Language Models
Figure 4 for Playing repeated games with Large Language Models
Viaarxiv icon

Invariant Neural Ordinary Differential Equations

Feb 26, 2023
Ilze Amanda Auzina, Çağatay Yıldız, Sara Magliacane, Matthias Bethge, Efstratios Gavves

Figure 1 for Invariant Neural Ordinary Differential Equations
Figure 2 for Invariant Neural Ordinary Differential Equations
Figure 3 for Invariant Neural Ordinary Differential Equations
Figure 4 for Invariant Neural Ordinary Differential Equations
Viaarxiv icon

Disentanglement and Generalization Under Correlation Shifts

Dec 29, 2021
Christina M. Funke, Paul Vicol, Kuan-Chieh Wang, Matthias Kümmerer, Richard Zemel, Matthias Bethge

Figure 1 for Disentanglement and Generalization Under Correlation Shifts
Figure 2 for Disentanglement and Generalization Under Correlation Shifts
Figure 3 for Disentanglement and Generalization Under Correlation Shifts
Figure 4 for Disentanglement and Generalization Under Correlation Shifts
Viaarxiv icon

Unsupervised Object Learning via Common Fate

Oct 13, 2021
Matthias Tangemann, Steffen Schneider, Julius von Kügelgen, Francesco Locatello, Peter Gehler, Thomas Brox, Matthias Kümmerer, Matthias Bethge, Bernhard Schölkopf

Figure 1 for Unsupervised Object Learning via Common Fate
Figure 2 for Unsupervised Object Learning via Common Fate
Figure 3 for Unsupervised Object Learning via Common Fate
Figure 4 for Unsupervised Object Learning via Common Fate
Viaarxiv icon

Visual Representation Learning Does Not Generalize Strongly Within the Same Domain

Jul 23, 2021
Lukas Schott, Julius von Kügelgen, Frederik Träuble, Peter Gehler, Chris Russell, Matthias Bethge, Bernhard Schölkopf, Francesco Locatello, Wieland Brendel

Figure 1 for Visual Representation Learning Does Not Generalize Strongly Within the Same Domain
Figure 2 for Visual Representation Learning Does Not Generalize Strongly Within the Same Domain
Figure 3 for Visual Representation Learning Does Not Generalize Strongly Within the Same Domain
Figure 4 for Visual Representation Learning Does Not Generalize Strongly Within the Same Domain
Viaarxiv icon

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

Jun 23, 2021
Roland S. Zimmermann, Judy Borowski, Robert Geirhos, Matthias Bethge, Thomas S. A. Wallis, Wieland Brendel

Figure 1 for How Well do Feature Visualizations Support Causal Understanding of CNN Activations?
Figure 2 for How Well do Feature Visualizations Support Causal Understanding of CNN Activations?
Figure 3 for How Well do Feature Visualizations Support Causal Understanding of CNN Activations?
Figure 4 for How Well do Feature Visualizations Support Causal Understanding of CNN Activations?
Viaarxiv icon

Partial success in closing the gap between human and machine vision

Jun 14, 2021
Robert Geirhos, Kantharaju Narayanappa, Benjamin Mitzkus, Tizian Thieringer, Matthias Bethge, Felix A. Wichmann, Wieland Brendel

Figure 1 for Partial success in closing the gap between human and machine vision
Figure 2 for Partial success in closing the gap between human and machine vision
Figure 3 for Partial success in closing the gap between human and machine vision
Figure 4 for Partial success in closing the gap between human and machine vision
Viaarxiv icon

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

May 27, 2021
Akis Linardos, Matthias Kümmerer, Ori Press, Matthias Bethge

Figure 1 for Calibrated prediction in and out-of-domain for state-of-the-art saliency modeling
Figure 2 for Calibrated prediction in and out-of-domain for state-of-the-art saliency modeling
Figure 3 for Calibrated prediction in and out-of-domain for state-of-the-art saliency modeling
Figure 4 for Calibrated prediction in and out-of-domain for state-of-the-art saliency modeling
Viaarxiv icon