RAHA applies rank-aware hyperbolic alignment to vision-language dataset distillation by enforcing geodesic alignment in the shared low-rank range and regularizing the residual subspace for improved transfer.
arXiv preprint arXiv:2312.16627 (2023)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Rank-Aware Hyperbolic Alignment for Vision-Language Dataset Distillation
RAHA applies rank-aware hyperbolic alignment to vision-language dataset distillation by enforcing geodesic alignment in the shared low-rank range and regularizing the residual subspace for improved transfer.