What is recorded here?
Reused selected token indices across layers to reduce sparse-attention indexing cost, with calibration-based layer selection and an optional multi-layer distillation objective.
Source-linked catalogue note. A detailed explanatory guide has not yet been prepared for this entry.
Scientific scope
DSA token selection is inherited. Approximate cross-layer index reuse is not exact equality to every layer's original selection. Reported speed/quality tradeoffs depend on calibration, retained indexers, model and hardware; later GLM naming is not another invention.
Read the original work
- IndexCache: Accelerating Sparse Attention via Cross-Layer Index Reuse
- Bai et al.: IndexCache cross-layer sparse-index reuse — official method source
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
Yushi Bai; Qian Dong; Ting Jiang; Xin Lv; Zhengxiao Du; Aohan Zeng; Jie Tang; Juanzi Li
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
Bai et al.: IndexCache cross-layer sparse-index reuse
Reused selected token indices across layers to reduce sparse-attention indexing cost, with calibration-based layer selection and an optional multi-layer distillation objective.
Scientific scope
DSA token selection is inherited. Approximate cross-layer index reuse is not exact equality to every layer's original selection. Reported speed/quality tradeoffs depend on calibration, retained indexers, model and hardware; later GLM naming is not another invention.
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
Yushi Bai; Qian Dong; Ting Jiang; Xin Lv; Zhengxiao Du; Aohan Zeng; Jie Tang; Juanzi Li
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.