cs.LGApr 8, 2026

Sheaf-Laplacian Obstruction and Projection Hardness for Cross-Modal Compatibility on a Modality-Independent Site

Authors: Tibor Sloboda

Organizations: UPAI, Faculty of Informatics and Information Technologies, Slovak University of Technology in Bratislava, Bratislava, Slovakia. · aleph0 s. r. o., Bratislava, Slovakia.

Abstract

Cross-modal representations vary in how easily they can be aligned, and compatibility is generally non-transitive: two modalities may align through an intermediate modality at lower complexity than through a direct map. We introduce a reference formalism that evaluates all modalities on a fixed neighborhood site and defines two directed invariants. Projection hardness Ha→b(ε)H_{a\to b}(\varepsilon) is the minimum complexity within a nested Lipschitz-controlled family required to reach error ε\varepsilon. For a declared local projection family, sheaf-Laplacian obstruction Ca→b(ε)C_{a\to b}(\varepsilon) is the minimum variation of locally fitted projection parameters required to reach the same error. Under identity restrictions, obstruction is the graph Dirichlet energy of a vector-valued parameter field; the sheaf formulation identifies zero energy with successful gluing and extends to edge-dependent transports and heterogeneous parameter spaces. We relate obstruction to the site spectral gap and excess global-map error, and construct ReLU examples showing non-transitive compatibility and a quadratic separation between staged and direct width. Controlled synthetic calibrations recover the predicted hardness separation, cut-induced obstruction scaling, and sensitivity to the fixed site graph.

Figures & tables

Explore similar work

CardsList
  1. Closing the Modality Gap via Simplex-Constrained Representations

    Oct 23, 2026Shubham Gupta, Siva Reddy, Perouz Taslakian +2Modality Gap in VLMsCross-Modal Alignment

  2. When to Align, When to Predict: A Phase Diagram for Multimodal Learning

    Jun 9, 2026Ilay Kamai, Hugues Van Assel, Aviv Regev +2Cross-Modal Representation LearningCross-Modal Alignment