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.
Dataset meta-learning from kernel ridge-regression
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
years
2026 7verdicts
UNVERDICTED 7representative citing papers
D3S2 combines class-balanced mask selection with diffusion-guided image synthesis and two consistency losses to distill 1% datasets that yield 24.99% mIoU on ADE20K and 35.49% on COCO-Stuff, beating random selection.
MDM distills vision-language datasets via joint embedding clustering, weight-space model interpolation, and geometry-aware distribution matching on the unit hypersphere.
Dataset distillation introduces fairness gaps from subgroup pattern mismatches rather than just imbalance; distilling to a group-agnostic barycenter of predictive information reduces these gaps.
HoPA captures high-order cross-modal alignments via a shared proxy to enable scalable omnimodal dataset distillation with better performance-compression trade-offs.
DO-ALL applies dataset distillation to generate synthetic source anchors that stabilize continual test-time adaptation under evolving domains without storing original source data.
SP-ESGC decouples graph condensation into heat-kernel node condensation and pre-trained edge prediction for structure, claiming high efficiency and cross-GNN generalization on real-world datasets.
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.
-
D3S2: Diffusion-Guided Dataset Distillation for Semantic Segmentation
D3S2 combines class-balanced mask selection with diffusion-guided image synthesis and two consistency losses to distill 1% datasets that yield 24.99% mIoU on ADE20K and 35.49% on COCO-Stuff, beating random selection.
-
Multimodal Distribution Matching for Vision-Language Dataset Distillation
MDM distills vision-language datasets via joint embedding clustering, weight-space model interpolation, and geometry-aware distribution matching on the unit hypersphere.
-
Fair Dataset Distillation via Cross-Group Barycenter Alignment
Dataset distillation introduces fairness gaps from subgroup pattern mismatches rather than just imbalance; distilling to a group-agnostic barycenter of predictive information reduces these gaps.
-
Omnimodal Dataset Distillation via High-order Proxy Alignment
HoPA captures high-order cross-modal alignments via a shared proxy to enable scalable omnimodal dataset distillation with better performance-compression trade-offs.
-
Distill Once, Adapt Life-Long: Exploring Dataset Distillation for Continual Test-Time Adaptation
DO-ALL applies dataset distillation to generate synthetic source anchors that stabilize continual test-time adaptation under evolving domains without storing original source data.
-
An Efficient and Scalable Graph Condensation with Structure-Preserving
SP-ESGC decouples graph condensation into heat-kernel node condensation and pre-trained edge prediction for structure, claiming high efficiency and cross-GNN generalization on real-world datasets.