Recoverable Compression: A Multimodal Vision Token Recovery Mechanism Guided by Text Information

Open Webpage

Yi Chen, Jian Xu, Xu-Yao Zhang, Wen-Zhuo Liu, Yang-Yang Liu, Cheng-Lin Liu

Published: 01 Jan 2025, Last Modified: 17 Apr 2025AAAI 2025EveryoneRevisionsBibTeXCC BY-SA 4.0