Heng Shu

CoRe-Diffusion: Bridging the Generative-Discriminative Gap in Dataset Distillation via Manifold-Aligned Contrastive Guidance

CoRe-Diffusion is proposed as a unified framework, which introduces Contrastive Negative Guidance, which utilizes inter-class mode centers—computed but largely unused during synthesis by existing methods—to exert zero-overhead repulsive gradients against hard negatives.