Unverified50% confidenceFactExact time
MoE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
1
Sources
50%
Confidence
Long-term
Relevance
7/25/2026
First Seen
Sources
中国开源大模型如何逼近美国闭源巨头？
Related Claims
VerifiedThe core idea of MoE (Mixture of Experts) can be traced back to the early mixture of experts framework proposed by Jacobs et al. in 1991, and Google's Switch Transformer in 2021 brought it into the era of large-scale language models.81% 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.80% similarVerifiedGoogle validated the Mixture of Experts (MoE) architecture at scale in Switch Transformer.78% 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)78% similarVerifiedThe MoE architecture was first proposed by Jacobs et al. in 1991 and in recent years has been brought back into the mainstream by models such as Google's Switch Transformer and Mixtral.76% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/615326API
curl https://kongchang.com/api/v1/knowledge/claims/615326MCP
get_claim(id=615326)