AI RESEARCH
ACE-Merging: Data-Free Model Merging with Adaptive Covariance Estimation
arXiv CS.CL
•
ArXi:2603.02945v2 Announce Type: replace Model merging aims to combine multiple task-specific expert models into a single model while preserving generalization across diverse tasks. However, interference among experts, especially when they are trained on different objectives, often leads to significant performance degradation. Despite recent progress, resolving this interference without data access, re