Author

Hanyong Shao

h-index 5 View on Semantic Scholar

We have 2 of 16 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Jul 2026

Recall Before You Rank: Similarity-Guided Top-K Reuse for Efficient Long-Context Attention

ReTopK is a training-free method that accelerates dynamic Top-$K$ attention by reusing historical retrieval decisions and retains the complete KV cache and reuses only selected indices, rather than historical scores, attention weights, or outputs.

Wen-Shuai Yao, Wen-Yong Zhou, Hanyong Shao et al. · arXiv.org · 0 citations

Jul 2026

CoSA: Accelerating Long-Context Inference via Proxy-Kernel Co-Designed Sparse Attention

CoSA is proposed, a two-stage training-free Sparse Attention under proxy-kernel CO-design, which couples a Kernel-Aware Proxy (KAP) with an Ordered-Skipping Kernel (OSK) and achieves a 4.93% attention speedup and reduces end-to-end Time-to-First-Token by 2.53% with negligible performance degradation.

Yufei Xue, Lin Niu, Hong Liu et al. · arXiv.org · 0 citations