Yingzhao Jian

Published on Aug 5 · Submitted by Yunqiu Xu on Aug 7 Abstract Understanding 3D scenes is fundamental to embodied intelligence, requiring joint reasoning over heterogeneous information from multiple modalities, including visual and geometric cues. However, the relevance of these modalities often varies across queries. Existing Multimodal Large Language Models (MLLMs) typically rely on fixed modality combinations, overlooking query-dependent modality needs.