AI RESEARCH
HiDe: Rethinking The Zoom-IN method in High Resolution MLLMs via Hierarchical Decoupling
arXiv CS.AI
•
ArXi:2510.00054v2 Announce Type: replace-cross Multimodal Large Language Models (MLLMs) have made significant strides in visual understanding tasks. However, their performance on high-resolution images remains suboptimal. While existing approaches often attribute this limitation to perceptual constraints and argue that MLLMs struggle to recognize small objects, leading them to use "zoom in" strategies for better detail, our analysis reveals a different cause: the main issue is not object size, but rather caused by complex background interference.