8 papers
Stable-GFlowNet: Toward Diverse and Robust LLM Red-Teaming via Contrastive Trajectory Balance
Minchan Kwon, Sunghyun Baek, Minseo Kim +3
Large Language Model (LLM) Red-Teaming, which proactively identifies vulnerabilities of LLMs, is an essential process for ensuring safety. Finding effective and diverse attacks in…
ConceptPrism: Concept Disentanglement in Personalized Diffusion Models via Residual Token Optimization
Minseo Kim, Minchan Kwon, Dongyeun Lee +2
Personalized text-to-image (T2I) generation has emerged as a key application for creating user-specific concepts from a few reference images. The core challenge is concept disentan…
Learning Question-Aware Keyframe Selection with Synthetic Supervision for Video Question Answering
Minchan Kwon, Hyounguk Shon, Junmo Kim
Large multimodal models (LMMs) have recently demonstrated remarkable performance in video question answering (VideoQA), yet reasoning over video remains challenging due to high inf…
FxSearcher: gradient-free text-driven audio transformation
Hojoon Ki, Jongsuk Kim, Minchan Kwon +1
Achieving diverse and high-quality audio transformations from text prompts remains challenging, as existing methods are fundamentally constrained by their reliance on a limited set…
Preference Distillation via Value based Reinforcement Learning
Minchan Kwon, Junwon Ko, Kangil Kim +1
Direct Preference Optimization (DPO) is a powerful paradigm to align language models with human preferences using pairwise comparisons. However, its binary win-or-loss supervision…
Comparison Reveals Commonality: Customized Image Generation through Contrastive Inversion
Minseo Kim, Minchan Kwon, Dongyeun Lee +2
The recent demand for customized image generation raises a need for techniques that effectively extract the common concept from small sets of images. Existing methods typically rel…