AI RESEARCH
GOMA: Toward Structure-Driven Multimodal Alignment from a Graph Signal Smoothing Perspective
arXiv CS.LG
•
ArXi:2605.15723v1 Announce Type: new Multimodal alignment is commonly learned from isolated image-text pairs via CLIP-style dual encoders, leaving the relational context among entities largely unused. Multimodal attributed graphs (MAGs), where nodes carry multimodal attributes and edges encode corpus structure, provide a natural setting for refining frozen vision-language embeddings. This refinement is challenging: visual, textual, and cross-modal relations often induce different neighborhood geometries, while unrestricted graph propagation can quickly over-smooth retrieval representations.