2026
Model Fusion via Retrofitting
Phoomraphee Luenam, Andreas Spanopoulos, Amit Sant, Sotiris Anagnostidis, Thomas Hofmann, Sidak Pal Singh
ICML 2026poster
Model fusion aims to combine the knowledge of multiple models by creating one representative model that captures the strengths of all of its parents. However, this process is non-trivial due to differences in internal representations, which can stem from permutation invariance, random initialization…