6 papers
Grokking of Diffusion Models: Case Study on Modular Addition
Joon Hyeok Kim, Yong-Hyun Park, Mattis Dalsætra Ãstby +1
Despite their empirical success, how diffusion models generalize remains poorly understood from a mechanistic perspective. We demonstrate that diffusion models trained with flow-ma…
APPLE: Attribute-Preserving Pseudo-Labeling for Diffusion-Based Face Swapping
Jiwon Kang, Yeji Choi, JoungBin Lee +6
Face swapping aims to transfer the identity of a source face onto a target face while preserving target-specific attributes such as pose, expression, lighting, skin tone, and makeu…
OmniGuide: Universal Guidance Fields for Enhancing Generalist Robot Policies
Yunzhou Song, Long Le, Yong-Hyun Park +7
Vision-language-action(VLA) models have shown great promise as generalist policies for a large range of relatively simple tasks. However, they demonstrate limited performance on mo…
Direct Unlearning Optimization for Robust and Safe Text-to-Image Models
Yong-Hyun Park, Sangdoo Yun, Jin-Hwa Kim +5
Recent advancements in text-to-image (T2I) models have unlocked a wide range of applications but also present significant risks, particularly in their potential to generate unsafe…
DECOR:Decomposition and Projection of Text Embeddings for Text-to-Image Customization
Geonhui Jang, Jin-Hwa Kim, Yong-Hyun Park +3
Text-to-image (T2I) models can effectively capture the content or style of reference images to perform high-quality customization. A representative technique for this is fine-tunin…
Geometric Remove-and-Retrain (GOAR): Coordinate-Invariant eXplainable AI Assessment
Yong-Hyun Park, Junghoon Seo, Bomseok Park +2
Identifying the relevant input features that have a critical influence on the output results is indispensable for the development of explainable artificial intelligence (XAI). Remo…