Unverified50% confidenceFactExact time
SWA (Sliding Window Attention) is a sparse attention variant that lets each token attend only to its neighbors within a fixed preceding window, reducing complexity to approximately linear.
1
Sources
50%
Confidence
Long-term
Relevance
10/13/2026
First Seen
Sources
Related Entities
Related Claims
Unverified新内核为滑动窗口注意力（SWA）层提供双输入支持，并引入 attention sinks 机制72% similarUnverified滑动窗口注意力（SWA）由 Mistral AI 广泛采用，将注意力复杂度从 O(N²) 降至 O(N×W)72% similarUnverifiedSwin Transformer introduced a local window attention mechanism.67% similarUnverified新一代模型通过稀疏注意力、滑动窗口注意力和检索增强生成（RAG）等技术大幅扩展了有效上下文长度65% similarVerifiedSliding Window Attention, adopted by models such as Mistral, limits each token's attention range to a fixed window.62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1014637API
curl https://kongchang.com/api/v1/knowledge/claims/1014637MCP
get_claim(id=1014637)