LGOct 10, 2025

Robustness and Regularization in Hierarchical Re-Basin

arXiv:2510.09174v21 citationsh-index: 1ESANN
Originality Incremental advance
AI Analysis

This work addresses model merging for AI practitioners, but it is incremental as it builds on existing Re-Basin techniques.

The paper investigates Git Re-Basin for merging trained models, proposing a hierarchical scheme that outperforms standard methods and induces robustness, but finds a larger performance drop than previously reported.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes