Author

Johannes Roth

1 paper indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#machine learning May 2026

Characterizing Universal Object Representations Across Vision Models

Differences in architecture, objective function, training data, model size, and model performance do not explain the emergence of universal dimensions, but models with more universal dimensions better predict macaque IT activity and human similarity judgments, suggesting that universality reflects representations relev...

Florian P. Mahner, Johannes Roth, Ka-Chun Lam et al. · arXiv.org · 3 citations