ICE: Task-Aligned Clifford Latent Fields for Multimodal Graph Foundation Models
Multimodal attributed graphs connect entities, visual content, language, and observed relations. Learning one foundation across such graphs requires more than compressing each node into a fused Euclidean vector. The representation must preserve entity semantics, construct interaction state from graph neighborhoods, and...
Xun-Kai Li, Xu Wang, Yin-Lin Zhu et al.
· 0 citations