Preprint
Aug 2026
Beyond Routing: Decoupling Expert Dispatch and Aggregation in Sparse Mixture-of-Experts
A cross-architecture distinction between expert selection and expert commitment is supported betweenparse Mixture-of-Experts (MoE) routers and DeepSeek-V2-Lite, which uses Top-6 routed experts plus shared experts.
Zongfei Li
· 0 citations