Picture for Robert Geirhos

Robert Geirhos

We Can't Understand AI Using our Existing Vocabulary

Add code
Feb 11, 2025
Viaarxiv icon

Do generative video models learn physical principles from watching videos?

Add code
Jan 14, 2025
Viaarxiv icon

Learning Visual Composition through Improved Semantic Guidance

Add code
Dec 19, 2024
Figure 1 for Learning Visual Composition through Improved Semantic Guidance
Figure 2 for Learning Visual Composition through Improved Semantic Guidance
Figure 3 for Learning Visual Composition through Improved Semantic Guidance
Figure 4 for Learning Visual Composition through Improved Semantic Guidance
Viaarxiv icon

Towards flexible perception with visual memory

Add code
Aug 15, 2024
Figure 1 for Towards flexible perception with visual memory
Figure 2 for Towards flexible perception with visual memory
Figure 3 for Towards flexible perception with visual memory
Figure 4 for Towards flexible perception with visual memory
Viaarxiv icon

How Aligned are Different Alignment Metrics?

Add code
Jul 10, 2024
Viaarxiv icon

Are Vision Language Models Texture or Shape Biased and Can We Steer Them?

Add code
Mar 14, 2024
Figure 1 for Are Vision Language Models Texture or Shape Biased and Can We Steer Them?
Figure 2 for Are Vision Language Models Texture or Shape Biased and Can We Steer Them?
Figure 3 for Are Vision Language Models Texture or Shape Biased and Can We Steer Them?
Figure 4 for Are Vision Language Models Texture or Shape Biased and Can We Steer Them?
Viaarxiv icon

Neither hype nor gloom do DNNs justice

Add code
Dec 08, 2023
Viaarxiv icon

Getting aligned on representational alignment

Add code
Nov 02, 2023
Viaarxiv icon

Intriguing properties of generative classifiers

Add code
Sep 28, 2023
Viaarxiv icon

Patch n' Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolution

Add code
Jul 12, 2023
Viaarxiv icon