作者位次 #4/9AAAI 2026Poster· Artificial Intelligence
D2 Prune: Sparsifying Large Language Models via Dual Taylor Expansion and Attention Distribution Awareness
Lang Xiong · Ning Liu · Ao Ren · Yuheng Bai · Haining Fang · Binyan Zhang · Zhe Jiang · Yujuan Tan · Duo Liu
效率与系统OpenReview