Unverified50% confidenceFactExact time
The basis used by AttSVD for low-rank compression is not fixed but is derived from each prompt's own attention geometry, retaining only the directions actually read by attention via online per-prompt truncated SVD.
1
Sources
50%
Confidence
Long-term
Relevance
10/7/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedAttSVD introduces a per-matrix energy rule that independently determines sizes for logit space and attention quality, dynamically adjusting the compression ratio.70% similarUnverifiedCompressed absorbing attention assigns each layer one of three modes—full, re-indexing, or reuse—to achieve inter-layer KV cache sharing.69% similarVerifiedThe Multi-Query Attention technique allows multiple attention heads to share a single set of Key and Value projection matrices, compressing KV cache memory requirements to 1/H of the original, at the cost of a slight reduction in model expressiveness.66% similarUnverified注意力层作为信息路由器在不同序列位置间聚合上下文，其键值是从提示中其他token动态派生的短期记忆表示64% similarUnverifiedFVD同时捕捉帧内视觉质量与帧间时序一致性，对长序列的漂移与身份崩溃现象较为敏感64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/983256API
curl https://kongchang.com/api/v1/knowledge/claims/983256MCP
get_claim(id=983256)