1.
Koike-Akino T, Chen X, Liu J, Wang Y, Wang P (Perry), Brand M. LatentLLM: Activation-Aware Transform to Multi-Head Latent Attention. AAAI [Internet]. 2026 Mar. 14 [cited 2026 May 13];40(27):22644-52. Available from: https://ojs.aaai.org/index.php/AAAI/article/view/39425