English

Robustness and Regularization in Hierarchical Re-Basin

Machine Learning 2026-05-20 v3

Abstract

This paper takes a closer look at Git Re-Basin, an interesting new approach to merge trained models. We propose a hierarchical model merging scheme that significantly outperforms the standard MergeMany algorithm. With our new algorithm, we find that Re-Basin induces adversarial and perturbation robustness into the merged models, with the effect becoming stronger the more models participate in the hierarchical merging scheme. However, in our experiments Re-Basin induces a much bigger performance drop than reported by the original authors.

Cite

@article{arxiv.2510.09174,
  title  = {Robustness and Regularization in Hierarchical Re-Basin},
  author = {Benedikt Franke and Florian Heinrich and Markus Lange and Arne Raulf},
  journal= {arXiv preprint arXiv:2510.09174},
  year   = {2026}
}

Comments

Published in 32th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, ESANN 2024

R2 v1 2026-07-01T06:28:59.043Z