[KongchangAI]
Unverified50% confidenceTradeoffExact time

双塔架构可预先计算并缓存一侧嵌入向量,查询时只需编码另一侧再做向量检索,计算量极低,这是CLM速度优势的架构根源;其代价是两侧编码器无法进行细粒度交叉注意力比对

1
Sources
50%
Confidence
Long-term
Relevance
10/4/2026
First Seen

Sources

Related Entities

Related Claims

Cite This Claim

Stable URI
https://kongchang.com/claim/973475
API
curl https://kongchang.com/api/v1/knowledge/claims/973475
MCP
get_claim(id=973475)