Review
Jul 2026
Multimodal Large Language Models for Remote Sensing Image Understanding: Domain-Specific or General-Purpose?
A systematic survey and diagnostic evaluation of MLLMs for RSISU and demonstrates the strong transferability of general-purpose CV-MLLMs and shows that current RS-MLLMs do not consistently outperform them across diverse RSISU tasks.
Qiwei Ma, Chun-Ping Qiu, Xinjun Cheng et al.
· arXiv.org · 0 citations