@inproceedings{shi-etal-2026-inheritance, title = "From Inheritance to Saturation: Disentangling the Evolution of Visual Redundancy for Architecture-Aware {MLLM} Inference Acceleration", author = "Shi, Jiaqi and Zhang, Xulong and Li, Yuechan and Qu, Xiaoyang and Wang, Jianzong", editor = "Liakata, Maria and Moreira, Viviane P. and Zhang, Jiajun and Jurgens, David", booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)", month = jul, year = "2026", address = "San Diego, California, United States", publisher = "Association for Computational Linguistics", url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.787/", pages = "17328--17357", ISBN = "979-8-89176-390-6" }