Sungho Koh — accepted AI-conference papers

2026

Adaptive Auxiliary Prompt Blending for Target-Faithful Diffusion Generation

Kwanyoung Lee, SeungJu Cha, Yebin Ahn, Hyunwoo Oh, Sungho Koh, Dong-Jin Kim

CVPR 2026

Diffusion-based text-to-image (T2I) models have made remarkable progress in generating photorealistic and semantically rich images. However, when the target concepts lie in low-density regions of the training distribution, these models often produce semantically misaligned or structurally inconsiste

Cited by 0 Source ↗Scholar ↗

2025

ScaleDiff: Higher-Resolution Image Synthesis via Efficient and Model-Agnostic Diffusion

Sungho Koh, SeungJu Cha, Hyunwoo Oh, Kwanyoung Lee, Dong-Jin Kim

NeurIPS 2025poster

Text-to-image diffusion models often exhibit degraded performance when generating images beyond their training resolution. Recent training-free methods can mitigate this limitation, but they often require substantial computation or are incompatible with recent Diffusion Transformer models. In this p…

Cited by 0 Source ↗Scholar ↗