8 papers
Keep It CALM: Analyzing the Limits of Global Unsafety in Text-to-Image Generation
NaHyeon Park, Minhyun Lee, Hyunjung Shim
Training-free safeguards for text-to-image generation often rely on a reusable safety signal, such as an unsafe direction or global toxic subspace, applied broadly across prompts.…
Grounding Driving VLA via Inverse Kinematics
Junsung Park, Hyunjung Shim
Existing Driving VLAs predict trajectories while largely ignoring their visual tokens -- a phenomenon we trace not to insufficient training but to a structurally ill-posed task for…
SGSoft: Learning Fused Semantic-Geometric Features for 3D Shape Correspondence via Template-Guided Soft Signals
Soyeon Yoon, Chang Wook Seo, Hyunjung Shim
Learning dense correspondences across deformable 3D shapes remains a long-standing challenge due to structural variability, non-isometric deformation, and inconsistent topology. Ex…
Representation Alignment for Just Image Transformers is not Easier than You Think
Jaeyo Shin, Jiwook Kim, Hyunjung Shim
Representation Alignment (REPA) has emerged as a simple way to accelerate Diffusion Transformers training in latent space. At the same time, pixel-space diffusion transformers such…
Rethinking the Use of Vision Transformers for AI-Generated Image Detection
NaHyeon Park, Kunhee Kim, Junsuk Choe +1
Rich feature representations derived from CLIP-ViT have been widely utilized in AI-generated image detection. While most existing methods primarily leverage features from the final…
Directional Textual Inversion for Personalized Text-to-Image Generation
Kunhee Kim, NaHyeon Park, Kibeom Hong +1
Textual Inversion (TI) is an efficient approach to text-to-image personalization but often fails on complex prompts. We trace these failures to embedding norm inflation: learned to…
Aligned but Stereotypical? How System Prompts Shape Demographic Bias in LLM-Based Text-to-Image Models
NaHyeon Park, Na Min An, Kunhee Kim +3
Text-to-image (T2I) systems increasingly rely on Large Language Model (LLM)-based text conditioning to interpret and expand user prompts. While this improves prompt understanding a…
TextBoost: Boosting Text Encoder for Personalized Text-to-Image Generation
NaHyeon Park, Kunhee Kim, Hyunjung Shim
In this paper, we introduce TextBoost, an efficient one-shot personalization approach for text-to-image diffusion models. Traditional personalization methods typically involve fine…