Showing cs.CVShow all
3 papers · 1 filter
cs.CV2026
MedVIGIL: Evaluating Trustworthy Medical VLMs Under Broken Visual Evidence
Hanqi Jiang, Junhao Chen, Mingyu Kang +12
Medical vision--language models (VLMs) are usually evaluated on intact image--question pairs, but trustworthy clinical use requires a stronger property: a model must recognise when…
cs.CV2026
LogoDiffuser: Training-Free Multilingual Logo Generation and Stylization via Letter-Aware Attention Control
Mingyu Kang, Hyein Seo, Yuna Jeong +2
Recent advances in text-to-image generation have been remarkable, but generating multilingual design logos that harmoniously integrate visual and textual elements remains a challen…
cs.CV2025
Editable Noise Map Inversion: Encoding Target-image into Noise For High-Fidelity Image Manipulation
Mingyu Kang, Yong Suk Choi
Text-to-image diffusion models have achieved remarkable success in generating high-quality and diverse images. Building on these advancements, diffusion models have also demonstrat…