Unverified50% confidenceFactExact time
MoE架构由多个专家子网络和一个路由器组成，路由器根据输入token动态选择少数几个专家参与计算，DeepSeek V2/V3、Mixtral 8x7B、Google Gemini 1.5均采用这一架构
1
Sources
50%
Confidence
Long-term
Relevance
7/17/2026
First Seen
Sources
Related Claims
UnverifiedThe MoE (Mixture of Experts) architecture was first proposed by Hinton's team in 2017, dynamically selecting Top-K expert sub-networks to participate in computation through a gated routing network.78% similarUnverifiedMoE架构由 Google Brain 于 2017 年提出，GPT-4、Mixtral 8x7B 等知名模型均采用该架构72% similarUnverifiedThe MoE architecture was founded on a Google paper from 2017; it dynamically assigns tokens to a small number of expert sub-networks via a routing network, and Qwen 3.5 122B has 122B total parameters but activates only approximately 22B during each inference.72% similarUnverified混合专家架构(MoE)的思路源于1991年的学术研究，近年被Mistral、DeepSeek、Google(Gemini 1.5)等广泛采用71% similarVerifiedThe Mixture of Experts (MoE) architecture was scaled up within the Transformer framework by Google Brain in 2017; its core idea is to group model parameters into multiple expert sub-networks, with only a small subset activated during each inference.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/544943API
curl https://kongchang.com/api/v1/knowledge/claims/544943MCP
get_claim(id=544943)