Auto-FlexSwitch: Efficient Dynamic Model Merging via Learnable Task Vector Compression

ArXi:2604.28109v1 Announce Type: new Model merging has attracted attention as an effective path toward multi-task adaptation by integrating knowledge from multiple task-specific models. Among existing approaches, dynamic merging mitigates performance degradation caused by conflicting parameter updates across tasks by flexibly combining task-specific parameters at inference time, thereby maintaining high performance. However, these methods require storing independent parameters for each task, resulting in prohibitive storage overhead.