C²R framework for robust dataset distillation prioritizes small-margin adversaries via a derived perturbation score and widens class boundaries with contrastive loss, yielding 2.8% average robust accuracy gains on CIFAR and ImageNet benchmarks.
arXiv preprint arXiv:2410.09140 , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
CoreUnlearn uses a Component Extraction Module and Swap Disentangling Strategy to remove only erasure-critical components from concept embeddings in diffusion models.
citing papers explorer
-
Mind Your Margin and Boundary: Are Your Distilled Datasets Truly Robust?
C²R framework for robust dataset distillation prioritizes small-margin adversaries via a derived perturbation score and widens class boundaries with contrastive loss, yielding 2.8% average robust accuracy gains on CIFAR and ImageNet benchmarks.
-
CoreUnlearn: Rethinking Concept Unlearning through Disentangled Component-Level Erasure in Text-guided Diffusion Models
CoreUnlearn uses a Component Extraction Module and Swap Disentangling Strategy to remove only erasure-critical components from concept embeddings in diffusion models.