#similarity retrieval

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

Wenshuai Yao, Wenyong Zhou, Hanyong Shao +5

The paper proposes ReTopK, a training‑free technique that speeds up dynamic top‑K sparse attention for long‑context language models by reusing supports from historically similar qu…