5 papers · 1 filter
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…
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…
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…
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…
FlowDPS: Flow-Driven Posterior Sampling for Inverse Problems
Jeongsol Kim, Bryan Sangwoo Kim, Jong Chul Ye
Flow matching is a recent state-of-the-art framework for generative modeling based on ordinary differential equations (ODEs). While closely related to diffusion models, it provides…