3 papers
cs.CV2025
Image Diffusion Models Exhibit Emergent Temporal Propagation in Videos
Youngseo Kim, Dohyun Kim, Geonhee Han +1
Image diffusion models, though originally developed for image generation, implicitly capture rich semantic structures that enable various recognition and localization tasks beyond…
eess.AS2025
DGMO: Training-Free Audio Source Separation through Diffusion-Guided Mask Optimization
Geonyoung Lee, Geonhee Han, Paul Hongsuck Seo
Language-queried Audio Source Separation (LASS) enables open-vocabulary sound separation via natural language queries. While existing methods rely on task-specific training, we exp…
cs.LG2025
Random Conditioning with Distillation for Data-Efficient Diffusion Model Compression
Dohyun Kim, Sehwan Park, Geonhee Han +2
Diffusion models generate high-quality images through progressive denoising but are computationally intensive due to large model sizes and repeated sampling. Knowledge distillation…