Yang X, Zhang J, Zhao D, Chen G, Tang Z. Self-Indexing KVCache: Predicting Sparse Attention from Compressed Keys. AAAI [Internet]. 2026 Mar. 14 [cited 2026 May 14];40(33):27675-83. Available from: https://ojs.aaai.org/index.php/AAAI/article/view/39988