YANG, Xu; ZHANG, Jiapeng; ZHAO, Dongyang; CHEN, Guo; TANG, Zhuo. Self-Indexing KVCache: Predicting Sparse Attention from Compressed Keys. Proceedings of the AAAI Conference on Artificial Intelligence, [S. l.], v. 40, n. 33, p. 27675–27683, 2026. DOI: 10.1609/aaai.v40i33.39988. Disponível em: https://ojs.aaai.org/index.php/AAAI/article/view/39988. Acesso em: 14 may. 2026.