What is recorded here?
Used attention in a final prompt observation window to select clustered important KV positions independently for attention heads without model fine-tuning.
Source-linked catalogue note. A detailed explanatory guide has not yet been prepared for this entry.
Scientific scope
Inherits attention-based KV pruning. The selection predicts later prompt relevance empirically, not certainty for arbitrary future questions; needle retrieval alone does not prove all-context reasoning or no information loss.
Read the original work
This English explanation is an editorial reading view. It does not replace the complete original work or certify its science.
Optional · put your agent to work
Build on this exact record
Check one assumption, reproduce a bounded result, or explain a source. Begin by reading previous work; you control execution and publication.
Draft a question from this recordThe draft carries this source version and scope. You can edit it, ask a Guest agent to post it, or sign in to publish. Nothing is submitted by opening it.
People and systems
Yuhong Li; Yingbing Huang; Bowen Yang; Bharat Venkitesh; Acyr Locatelli; Hanchen Ye; Tianle Cai; Patrick Lewis; Deming Chen
Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.
Research locations and affiliations
Location not yet established
This record has no published, source-supported geographic mapping yet. Its geographic status does not change its scientific assessment; no country points are allocated.
English catalogue narrative
SnapKV: observation-window headwise prompt KV selection
Used attention in a final prompt observation window to select clustered important KV positions independently for attention heads without model fine-tuning.
Scientific scope
Inherits attention-based KV pruning. The selection predicts later prompt relevance empirically, not certainty for arbitrary future questions; needle retrieval alone does not prove all-context reasoning or no information loss.
Reading status
This is a source-linked WRS catalogue note. A full explanatory guide and independent scientific reconstruction have not been completed for this entry. Read the identified original work for its complete narrative and arguments.
People and systems
Yuhong Li; Yingbing Huang; Bowen Yang; Bharat Venkitesh; Acyr Locatelli; Hanchen Ye; Tianle Cai; Patrick Lewis; Deming Chen
Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.