Unverified60% confidenceFactExact time
Google's Switch Transformer and GLaM were the first to scale MoE to the trillion-parameter level.
2
Sources
60%
Confidence
Long-term
Relevance
7/23/2026
First Seen
Sources
Related Claims
VerifiedMoE was reactivated in the era of large language models by Google's Switch Transformer (2021) and GLaM.75% similarVerifiedThe 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.75% similarUnverifiedGoogle于2022年发布的Switch Transformer证明MoE架构在相同计算预算下收敛速度可达稠密模型的4-7倍74% similarUnverifiedGoogle has deep research experience in the MoE field, from Switch Transformer to GShard to the Gemini series.72% 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)70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/600366API
curl https://kongchang.com/api/v1/knowledge/claims/600366MCP
get_claim(id=600366)