AI RESEARCH
On the Spectral Geometry of Cross-Modal Representations: A Functional Map Diagnostic for Multimodal Alignment
arXiv CS.AI
•
ArXi:2604.08579v1 Announce Type: cross We study cross-modal alignment between independently pretrained vision (DINOv2) and language (all-MiniLM-L6-v2) encoders using the functional map framework from computational geometry, which represents correspondence between representation manifolds as a compact linear operator between graph Laplacian eigenbases. While the framework underperforms Procrustes alignment and relative representations for cross-modal retrieval across all supervision budgets, it reveals a structural property of multimodal representations.