<ul><li>Combining multiple machine learning models has been a technique for enhancing performance.</li><li>Traditional approaches like model ensembles are expensive in terms of memory and compute.</li><li>Methods based on averaging model parameters have gained popularity but can yield worse results with differently initialized models.</li><li>Non-uniform Parameter-wise Model Merging (NP Merge) is introduced as a novel approach, achieving better results for merging models of various architectures.</li></ul>

Non-Uniform Parameter-Wise Model Merging

Discover more