Junhui He, Zhihui Fu, Jun Wang, Qingan Li. POP: Prefill-Only Pruning for Efficient Large Model Inference. In Maria Liakata, Viviane P. Moreira, Jiajun Zhang 0001, David Jurgens, editors, Findings of the Association for Computational Linguistics, ACL 2026, San Diego, California, United States, July 2-7, 2026. pages 5864-5877, Association for Computational Linguistics, 2026. [doi]
Abstract is missing.