AI RESEARCH

DC-Merge: Improving Model Merging with Directional Consistency

arXiv CS.LG

ArXi:2603.06242v1 Announce Type: new Model merging aims to integrate multiple task-adapted models into a unified model that preserves the knowledge of each task. In this paper, we identify that the key to this knowledge retention lies in maintaining the directional consistency of singular spaces between merged multi-task vector and individual task vectors.