Independently trained vision and language models develop representation manifolds of comparable intrinsic complexity but with unaligned eigenvector bases, creating a spectral complexity-orientation gap.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
On the Spectral Geometry of Cross-Modal Representations: A Functional Map Diagnostic for Multimodal Alignment
Independently trained vision and language models develop representation manifolds of comparable intrinsic complexity but with unaligned eigenvector bases, creating a spectral complexity-orientation gap.