Unverified50% confidenceFactExact time

标准Transformer自注意力对于长度为T的序列需要O(T²)次点积运算和T×T大小的注意力矩阵

1

Sources

50%

Confidence

Long-term

Relevance

8/24/2026

First Seen

Sources

CWAA Architecture Explained: Replacing Transformer Attention with Complex Wave Dynamics

Related Entities

Transformerconcept

Related Claims

VerifiedThe self-attention mechanism of the standard Transformer architecture has a computational complexity of O(n²).77% similar UnverifiedSet Transformer的诱导点注意力ISAB通过m个可学习诱导点将O(n²)注意力复杂度降至O(mn)77% similar

Cite This Claim

Stable URI

https://kongchang.com/claim/795590

API

curl https://kongchang.com/api/v1/knowledge/claims/795590

MCP

get_claim(id=795590)