4 papers · 1 filter
Self-Improving Diffusion Classifiers with Minority Preference Optimization
Hyunsoo Kim, Jungmyung Wi, Soobin Um +2
Prior studies have demonstrated that diffusion classifiers achieve robust zero-shot classification performance. However, their effectiveness is strongly tied to the pretraining dat…
MotionCFG: Boosting Motion Dynamics via Stochastic Concept Perturbation
Byungjun Kim, Soobin Um, Jong Chul Ye
Despite recent advances in Text-to-Video (T2V) synthesis, generating high-fidelity and dynamic motion remains a significant challenge. Existing methods primarily rely on Classifier…
Minority-Focused Text-to-Image Generation via Prompt Optimization
Soobin Um, Jong Chul Ye
We investigate the generation of minority samples using pretrained text-to-image (T2I) latent diffusion models. Minority instances, in the context of T2I generation, can be defined…
Self-Guided Generation of Minority Samples Using Diffusion Models
Soobin Um, Jong Chul Ye
We present a novel approach for generating minority samples that live on low-density regions of a data manifold. Our framework is built upon diffusion models, leveraging the princi…