Unverified50% confidenceFactExact time
Google has deep research experience in the MoE field, from Switch Transformer to GShard to the Gemini series.
1
Sources
50%
Confidence
Long-term
Relevance
9/3/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedAfter the successful deployment of MoE models represented by Google Switch Transformer and Mixtral, the MoE architecture has become the mainstream technical choice for ultra-large-scale language models.74% similarVerifiedThe MoE architecture was proposed by Shazeer et al. in 2017 in the paper "Outrageously Large Neural Networks" and subsequently validated at scale by Google in Switch Transformer (2021)74% similarUnverifiedThe modern form of MoE can be traced back to a Google paper in 2017, and in 2022 Google's Switch Transformer demonstrated that trillion-parameter sparse models can be trained efficiently.73% similarUnverifiedGoogle Brain于2017年在《Outrageously Large Neural Networks》论文中将MoE规模化应用于Transformer框架73% similarUnverifiedMoE混合专家架构最早可追溯至1991年的学术论文，谷歌于2021年发布Switch Transformer将专家数量扩展至2048个73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/851721API
curl https://kongchang.com/api/v1/knowledge/claims/851721MCP
get_claim(id=851721)