---
format: "aidr-story-markdown/v1"
id: "8d15341568ded10f567a3b855553934f00d800158c5da5164513717c59308834"
canonical_url: "https://aidr.today/8d153415?lang=en"
title: "Meta Expert: Cross-Layer Expert Sharing for Storage- and Retrieval-Efficient MoE"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-10-23T00:00:00.000Z"
category: "Research"
topics: ["meta","llm"]
source_urls: ["https://huggingface.co/papers/2610.27598"]
summary: "Researchers proposed Cross-Layer Expert Sharing for Storage- and Retrieval-Efficient MoE, finding that inter-layer shared Meta Experts reduce parameter redundancy and improve cross-entropy loss and downstream task accuracy compared to hierarchical Local Experts. Their model matches Vanilla MoE performance using only 70-80% of the experts when activated quantity and expert granularity are held fixed."
---

# Meta Expert: Cross\-Layer Expert Sharing for Storage\- and Retrieval\-Efficient MoE

> [Open the canonical story](<https://aidr.today/8d153415?lang=en>)

**Published:** 2026-10-23T00:00:00.000Z
**Category:** Research
**Topics:** meta, llm

## Summary

Researchers proposed Cross\-Layer Expert Sharing for Storage\- and Retrieval\-Efficient MoE, finding that inter\-layer shared Meta Experts reduce parameter redundancy and improve cross\-entropy loss and downstream task accuracy compared to hierarchical Local Experts\. Their model matches Vanilla MoE performance using only 70\-80% of the experts when activated quantity and expert granularity are held fixed\.

## Sources

- [Story source](<https://huggingface.co/papers/2610.27598>)