Research
Meta Expert proposes cross-layer shared experts to make MoE models more storage-efficient
The research shares experts across layers and reports matching Vanilla MoE performance using only 70 to 80 percent of the experts, with the same activated count and granularity.
Every outlet that ran it 1 article
Hugging Face PapersResearchLead
Meta Expert: Cross-Layer Expert Sharing for Storage- and Retrieval-Efficient MoE