Furu Wei
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
NLP×1AI×1ML×1
Frequent co-authors
Research Timeline
2026
You Only Index Once: Cross-Layer Sparse Attention with Shared Routing
The paper proposes Cross-Layer Sparse Attention (CLSA) to significantly improve the efficiency and accuracy of long-context LLMs by jointly optimizing KV-cache sharing and the routing index across decoder layers.
Highlighted terms show continued research focus across papers
Papers
cs.CLcs.AIcs.LGRecentJun 4, 2026
You Only Index Once: Cross-Layer Sparse Attention with Shared Routing
Yutao Sun, Yanqi Zhang, Li Dong, Jianyong Wang +1 more
The paper proposes Cross-Layer Sparse Attention (CLSA) to significantly improve the efficiency and accuracy of long-context LLMs by jointly optimizing KV-cache sharing and the routing index across dec…
View →