AI RESEARCH

Semantic-Geometric Dual Compression: Training-Free Visual Token Reduction for Ultra-High-Resolution Remote Sensing Understanding

arXiv CS.AI

ArXi:2604.11122v1 Announce Type: cross Multimodal Large Language Models (MLLMs) have nstrated immense potential in Earth observation. However, the massive visual tokens generated when processing Ultra-High-Resolution (UHR) imagery