Tian H, Lu S, Tian F, Cui G, Li Z, Zhang X, et al. DIAA: A Decoding-Efficient Inference Acceleration Approach for On-Device Large Language Models. AAAI [Internet]. 2026 Mar. 14 [cited 2026 May 14];40(31):25896-904. Available from: https://ojs.aaai.org/index.php/AAAI/article/view/39789