{"ID":2857449,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.09174","arxiv_id":"2510.09174","title":"Robustness and Regularization in Hierarchical Re-Basin","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.","short_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 merg...","url_abs":"https://arxiv.org/abs/2510.09174","url_pdf":"https://arxiv.org/pdf/2510.09174v3","authors":"[\"Benedikt Franke\",\"Florian Heinrich\",\"Markus Lange\",\"Arne Raulf\"]","published":"2025-10-10T09:17:10Z","proceeding":"cs.LG","tasks":"[\"cs.LG\"]","methods":"[]","has_code":false}