mlsanityData to 14 Oct 2026

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

arXiv 2604.07632 ↗First posted 8 Apr 2026cs.LG cs.AIcited by 1

Not on the map. Why?

Abstract (arXiv)

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(varepsilon)) is the minimum complexity within a nested Lipschitz-controlled family required to reach error (varepsilon). For a declared local projection family, sheaf-Laplacian obstruction (Ca→ 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.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 14 of its 31 references that are in the map. First posted on arXiv 8 Apr 2026.

Builds on

14 of 31 references.

References · 14

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2017Multimodal Machine Learning: A Survey and Taxonomycited by 1,013
  3. 2017Spectrally-normalized margin bounds for neural networkscited by 686
  4. 2023NExT-GPT: Any-to-Any Multimodal LLMcited by 615
  5. 2017Size-Independent Sample Complexity of Neural Networkscited by 290
  6. 2016Benefits of depth in neural networkscited by 250
  7. 2022Neural Sheaf Diffusion: A Topological Perspective on Heterophily and Oversmoothing in GNNscited by 214
  8. 2021Revisiting Model Stitching to Compare Neural Representationscited by 209
  9. 2023Getting aligned on representational alignmentcited by 143
  10. 2020Sheaf Neural Networkscited by 84
  11. 2018Universal Neural Machine Translation for Extremely Low Resource Languagescited by 66
  12. 2019Transfer Learning for Nonparametric Classification: Minimax Rate and Adaptive Classifiercited by 65
2 more
  1. 2016Zero-Resource Translation with Multi-Lingual Neural Machine Translationcited by 46
  2. 2023Dirac signal processing of higher-order topological signalscited by 9

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.