Unverified50% confidenceFactExact time
MoE架构可追溯到1991年Jacobs等人的工作，但直到2022年后才在大语言模型中大规模应用
1
Sources
50%
Confidence
Long-term
Relevance
8/28/2026
First Seen
Sources
Related Entities
Related Claims
Unverified混合专家架构最早由Jacobs等人在1991年提出，但直到2022-2024年才在大语言模型领域大规模应用78% similarUnverifiedMoE 架构自2022年前后在大语言模型领域广泛普及，Mixtral、DeepSeek-V2、MiniMax M3均是典型实践者68% similarVerifiedDoubao is a large language model series launched by ByteDance in 2023, iteratively developed based on its self-developed Skylark model architecture.59% similarUnverifiedSince 2023, the BDI architecture has been reactivated following the leap in large language model capabilities.58% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/810542API
curl https://kongchang.com/api/v1/knowledge/claims/810542MCP
get_claim(id=810542)