From Inheritance to Saturation: Disentangling the Evolution of Visual Redundancy for Architecture-Aware MLLM Inference Acceleration
Abstract
TBD
Type
Publication
In The 64th Annual Meeting of the Association for Computational Linguistics
Click the Cite button above to demo the feature to enable visitors to import publication metadata into their reference management software.
Jiaqi Shi
University of Science and Technology of China
