نسخة أولية وصول مفتوح
The Earth in One Gaze: Training-Free Active Focus for UHR Remote Sensing Understanding
Multimodal large language models (MLLMs) must balance local detail against scene context when interpreting ultra-high-resolution (UHR) remote sensing (RS) imagery within a limited visual-input budget. Existing selection-based methods either prune tokens and select patches through relevance scoring, or crop actively thr …