Task Alignment: A simple and effective proxy for model merging in computer vision

ArXi:2604.12935v1 Announce Type: new Efficiently merging several models fine-tuned for different tasks, but stemming from the same pretrained base model, is of great practical interest. Despite extensive prior work, most evaluations of model merging in computer vision are restricted to image classification using CLIP, where different classification datasets define different tasks. In this work, our goal is to make model merging practical and show its relevance on challenging scenarios beyond this specific setting.