3 papers
cs.CV2025
MMPB: It's Time for Multi-Modal Personalization
Jaeik Kim, Woojin Kim, Woohyeon Park +1
Visual personalization is essential in user-facing AI systems such as smart homes and healthcare, where aligning model behavior with user-centric concepts is critical. However, rec…
cs.CV2025
SECOND: Mitigating Perceptual Hallucination in Vision-Language Models via Selective and Contrastive Decoding
Woohyeon Park, Woojin Kim, Jaeik Kim +1
Despite significant advancements in Vision-Language Models (VLMs), the performance of existing VLMs remains hindered by object hallucination, a critical challenge to achieving accu…
cs.CV2025
A Training-Free Style-aligned Image Generation with Scale-wise Autoregressive Model
Jihun Park, Jongmin Gim, Kyoungmin Lee +5
We present a training-free style-aligned image generation method that leverages a scale-wise autoregressive model. While large-scale text-to-image (T2I) models, particularly diffus…