activity
20242026
collaborators

5 papers

cs.CV2026

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…

cs.GR2025

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…

physics.optics2025

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…

cs.LG2025

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…

cs.CV2024

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…