AI RESEARCH
Path-Constrained Mixture-of-Experts
arXiv CS.LG
•
ArXi:2603.18297v1 Announce Type: new Sparse Mixture-of-Experts (MoE) architectures enable efficient scaling by activating only a subset of parameters for each input. However, conventional MoE routing selects each layer's experts independently, creating N^L possible expert paths -- for N experts across L layers. This far exceeds typical