Path-Constrained Mixture-of-Experts
arXiv:2603.18297v1 Announce Type: new Abstract: Sparse Mixture-of-Experts (MoE) architectures enable efficient scaling by activating only a subset of parameters for each input. However, conventional MoE …
Zijin Gu, Tatiana Likhomanenko, Vimal Thilak, Jason Ramapuram, Navdeep Jaitly
조회수 38회