AI RESEARCH
Let Geometry GUIDE: Layer-wise Unrolling of Geometric Priors in Multimodal LLMs
arXiv CS.CV
•
ArXi:2604.05695v1 Announce Type: new Multimodal Large Language Models (MLLMs) have achieved remarkable progress in 2D visual tasks but still exhibit limited physical spatial awareness when processing real-world visual streams. Recently, feed-forward geometric foundation models, which implicitly extract geometric priors, have provided a new pathway to address this issue. However, existing geometry-aware MLLMs are predominantly constrained by the paradigm of single deep-layer extraction and input-level fusion.