Xiong L, Liu N, Ren A, Bai Y, Fang H, Zhang B, et al. D2 Prune: Sparsifying Large Language Models via Dual Taylor Expansion and Attention Distribution Awareness. AAAI [Internet]. 2026 Mar. 14 [cited 2026 May 27];40(32):27171-9. Available from: https://ojs.aaai.org/index.php/AAAI/article/view/39932