Author name: Yuliang Li, Chu Zhou, Heng Guo, Boxin Shi, Imari Sato, Zhanyu Ma

arXiv:2605.07574v2 Announce Type: replace
Abstract: Mainstream vision-language models (VLMs) fundamentally struggle with severe optical ambiguities, such as reflections and transparent objects, due to the inherent limitations of standard RGB inputs. W…

arXiv:2605.07574v1 Announce Type: new
Abstract: Mainstream vision-language models (VLMs) fundamentally struggle with severe optical ambiguities, such as reflections and transparent objects, due to the inherent limitations of standard RGB inputs. While…