activity
20242026
collaborators

8 papers

cs.CV2026

Tiled Prompts: Overcoming Prompt Misguidance in Image and Video Super-Resolution

Bryan Sangwoo Kim, Jonghyun Park, Jong Chul Ye

Text-conditioned diffusion models have advanced image and video super-resolution by using prompts as semantic priors, and modern super-resolution pipelines typically rely on latent…

cs.CV2026

Chain-of-Zoom: Extreme Super-Resolution via Scale Autoregression and Preference Alignment

Bryan Sangwoo Kim, Jeongsol Kim, Jong Chul Ye

Modern single-image super-resolution (SISR) models deliver photo-realistic results at the scale factors on which they are trained, but collapse when asked to magnify far beyond tha…

cs.CV2026

Align Your Query: Representation Alignment for Multimodality Medical Object Detection

Ara Seo, Bryan Sangwoo Kim, Hyungjin Chung +1

Medical object detection suffers when a single detector is trained on mixed medical modalities (e.g., CXR, CT, MRI) due to heterogeneous statistics and disjoint representation spac…

cs.CV2025

FreeGuide: Training-Free Text-to-Video Alignment using Image LVLM

Jaemin Kim, Bryan Sangwoo Kim, Jong Chul Ye

Diffusion models have achieved impressive results in generative tasks for text-to-video (T2V) synthesis. However, achieving accurate text alignment in T2V generation remains challe…

cs.CV2025

Extreme Blind Image Restoration via Prompt-Conditioned Information Bottleneck

Hongeun Kim, Bryan Sangwoo Kim, Jong Chul Ye

Blind Image Restoration (BIR) methods have achieved remarkable success but falter when faced with Extreme Blind Image Restoration (EBIR), where inputs suffer from severe, compounde…

cs.OS2025

Preparation Meets Opportunity: Enhancing Data Preprocessing for ML Training With Seneca

Omkar Desai, Ziyang Jiao, Shuyi Pei +2

Input data preprocessing is a common bottleneck when concurrently training multimedia machine learning (ML) models in modern systems. To alleviate these bottlenecks and reduce the…