7 papers
Safety for Whom? Benchmarking Understanding Beyond Refusal in Egocentric Multimodal Assistants
Yewon Han, Jisu Jeon, Suhyun Choi +5
Egocentric multimodal assistants see through the user's eyes and guide what the user does next, so their outputs directly shape physical actions, including those that affect bystan…
Correcting Guided Diffusion Trajectories with Spectral Alignment
Gihoon Kim, Taesup Kim
The practical success of conditional image generation hinges on fine-grained differences in condition alignment and visual fidelity. Classifier-free guidance (CFG) is central to th…
Cautious Context Steering for Language Model Personalization
Gihoon Kim, Jeyoung Lee, Suhan Woo +4
Personalizing language models (LMs) to individual user preferences is essential for aligning responses with diverse goals and backgrounds. Existing methods typically train a separa…
Anchor to Expand: Semantic Anchoring for Personalized Text-to-Image Diffusion Models
Seoyun Yang, Gihoon Kim, Taesup Kim
Personalizing text-to-image diffusion models extends pretrained models to represent novel user-specific concepts from only a few reference images. However, learning a new concept w…
Assessing Socio-Cultural Alignment and Technical Safety of Sovereign LLMs
Kyubyung Chae, Gihoon Kim, Gyuseong Lee +3
Recent trends in LLMs development clearly show growing interest in the use and application of sovereign LLMs. The global debate over sovereign LLMs highlights the need for governme…
Preserve and Personalize: Personalized Text-to-Image Diffusion Models without Distributional Drift
Gihoon Kim, Hyungjin Park, Taesup Kim
Personalizing text-to-image diffusion models involves integrating novel visual concepts from a small set of reference images while retaining the model's original generative capabil…
NeRFFaceSpeech: One-shot Audio-driven 3D Talking Head Synthesis via Generative Prior
Gihoon Kim, Kwanggyoon Seo, Sihun Cha +1
Audio-driven talking head generation is advancing from 2D to 3D content. Notably, Neural Radiance Field (NeRF) is in the spotlight as a means to synthesize high-quality 3D talking…