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…
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…
cs.LG2024
Learning from Convolution-based Unlearnable Datasets
Dohyun Kim, Pedro Sandoval-Segura
The construction of large datasets for deep learning has raised concerns regarding unauthorized use of online data, leading to increased interest in protecting data from third-part…