Matthias Bethge

6

Papers

55

Total Citations

Papers (6)

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

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

VGGSounder: Audio-Visual Evaluations for Foundation Models

How to Merge Your Multimodal Models Over Time?

Modeling Saliency Dataset Bias

The Entropy Enigma: Success and Failure of Entropy Minimization