MIRROR derives a closed-form Semi-Inverse Gromov-Wasserstein loss to align language-derived relational priors with visual representations inside decoder-only Transformers.
arXiv preprint arXiv:2501.10573 , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Common ID estimators fail to track the true intrinsic dimension of neural representations and are instead driven by other factors.
citing papers explorer
-
MIRROR: Aligning Semantic Relations from Language to Image via Gromov--Wasserstein
MIRROR derives a closed-form Semi-Inverse Gromov-Wasserstein loss to align language-derived relational priors with visual representations inside decoder-only Transformers.
-
Rethinking Intrinsic Dimension Estimation in Neural Representations
Common ID estimators fail to track the true intrinsic dimension of neural representations and are instead driven by other factors.