7 papers
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…
Beyond Generative Priors: Minority Sampling with JEPA-Guided Diffusion
Sol Park, Soobin Um
Minority sampling aims to generate low-density instances on a data manifold and is of central importance in applications such as medical diagnosis, anomaly detection, and creative…
Diverse Text-to-Image Generation via Contrastive Noise Optimization
Byungjun Kim, Soobin Um, Jong Chul Ye
Text-to-image (T2I) diffusion models have demonstrated impressive performance in generating high-fidelity images, largely enabled by text-guided inference. However, this advantage…
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…
Boost-and-Skip: A Simple Guidance-Free Diffusion for Minority Generation
Soobin Um, Beomsu Kim, Jong Chul Ye
Minority samples are underrepresented instances located in low-density regions of a data manifold, and are valuable in many generative AI applications, such as data augmentation, c…
Physics-guided and fabrication-aware inverse design of photonic devices using diffusion models
Dongjin Seo, Soobin Um, Sangbin Lee +2
Designing free-form photonic devices is fundamentally challenging due to the vast number of possible geometries and the complex requirements of fabrication constraints. Traditional…