Paper

Geometry-Aware Dataset Condensation for Diffusion Model Training

arXiv:2606.05883v1 Announce Type: new Abstract: Dataset condensation aims to construct compact datasets from real data via synthesis or selection. However, existing approaches are ill-suited for diffusion model training: synthetic data generation often yields low-fidelity samples unsuitable for authentic modeling, while real subset selection typically fails to preserve the distributional geometry required by diffusion likelihood objectives. To address this, we propose to reformulate real subset selection as a geometry-aware distribution alignment problem. By incorporating one-sided partial op…

Authors:

Related discussions