1 citations · 1 across the 8 of their papers we have counts for
13 papers
MaDeL: Manifold-Decomposed Feature Losses for Generative Modeling
Beomsu Kim, Jong Chul Ye, Kwanyoung Kim
Generative models are often trained with isotropic objectives such as mean-squared error. For data concentrated near a low-dimensional manifold, however, such losses conflate displ…
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…
Generalizable Holographic Reconstruction via Amplitude-Only Diffusion Priors
Jeongsol Kim, Chanseok Lee, Jongin You +2
Phase retrieval in inline holography is a fundamental yet ill-posed inverse problem due to the nonlinear coupling between amplitude and phase in coherent imaging. We present a nove…
Diffusion models for inverse problems
Hyungjin Chung, Jeongsol Kim, Jong Chul Ye
Using diffusion priors to solve inverse problems in imaging have significantly matured over the years. In this chapter, we review the various different approaches that were propose…
FlowAlign: Trajectory-Regularized, Inversion-Free Flow-based Image Editing
Jeongsol Kim, Yeobin Hong, Jonghyun Park +1
Recent inversion-free, flow-based image editing methods such as FlowEdit leverages a pre-trained noise-to-image flow model such as Stable Diffusion 3, enabling text-driven manipula…
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…
Aligning Text to Image in Diffusion Models is Easier Than You Think
Jaa-Yeon Lee, Byunghee Cha, Jeongsol Kim +1
While recent advancements in generative modeling have significantly improved text-image alignment, some residual misalignment between text and image representations still remains.…
Latent Schrodinger Bridge: Prompting Latent Diffusion for Fast Unpaired Image-to-Image Translation
Jeongsol Kim, Beomsu Kim, Jong Chul Ye
Diffusion models (DMs), which enable both image generation from noise and inversion from data, have inspired powerful unpaired image-to-image (I2I) translation algorithms. However,…
Improving Factuality of 3D Brain MRI Report Generation with Paired Image-domain Retrieval and Text-domain Augmentation
Junhyeok Lee, Yujin Oh, Dahyoun Lee +9
Acute ischemic stroke (AIS) requires time-critical decision-making, where inaccurate interpretation of neuroimaging findings can lead to irreversible disability. Diffusion-weighted…
Simple ReFlow: Improved Techniques for Fast Flow Models
Beomsu Kim, Yu-Guan Hsieh, Michal Klein +4
Diffusion and flow-matching models achieve remarkable generative performance but at the cost of many sampling steps, this slows inference and limits applicability to time-critical…
(Deep) Generative Geodesics
Beomsu Kim, Michael Puthawala, Jong Chul Ye +1
In this work, we propose to study the global geometrical properties of generative models. We introduce a new Riemannian metric to assess the similarity between any two data points.…