1
When Model Merging Breaks Routing: Training-Free Calibration for MoE
揭示模型合并对MoE路由的破坏机制，提出无需训练的高效校准方案，为混合专家模型优化提供新思路。
arXiv:2606.03391v1 Announce Type: cross Abstract: Model merging has emerged as a cost-effective approach for consolidating the capabilities of multipl…