11 papers
Physics in 2-Steps: Locking Motion Priors Before Visual Refinement Erases Them
Woojung Han, Seil Kang, Youngjun Jun +3
Image-to-Video diffusion models leverage input images to generate visually stunning content, yet frequently produce motion that violates physical laws. We reveal a surprising findi…
Real-Time Visual Attribution Streaming in Thinking Model
Seil Kang, Woojung Han, Junhyeok Kim +3
We present an amortized framework for real-time visual attribution streaming in multimodal thinking models. When these models generate code from a screenshot or solve math problems…
Interpretable Motion-Attentive Maps: Spatio-Temporally Localizing Concepts in Video Diffusion Transformers
Youngjun Jun, Seil Kang, Woojung Han +1
Video Diffusion Transformers (DiTs) have been synthesizing high-quality video with high fidelity from given text descriptions involving motion. However, understanding how Video DiT…
Rare Text Semantics Were Always There in Your Diffusion Transformer
Seil Kang, Woojung Han, Dayun Ju +1
Starting from flow- and diffusion-based transformers, Multi-modal Diffusion Transformers (MM-DiTs) have reshaped text-to-vision generation, gaining acclaim for exceptional visual f…
PRETI: Patient-Aware Retinal Foundation Model via Metadata-Guided Representation Learning
Yeonkyung Lee, Woojung Han, Youngjun Jun +3
Retinal foundation models have significantly advanced retinal image analysis by leveraging self-supervised learning to reduce dependence on labeled data while achieving strong gene…
Spatial Transport Optimization by Repositioning Attention Map for Training-Free Text-to-Image Synthesis
Woojung Han, Yeonkyung Lee, Chanyoung Kim +2
Diffusion-based text-to-image (T2I) models have recently excelled in high-quality image generation, particularly in a training-free manner, enabling cost-effective adaptability and…
Pathology-Aware Adaptive Watermarking for Text-Driven Medical Image Synthesis
Chanyoung Kim, Dayun Ju, Jinyeong Kim +3
As recent text-conditioned diffusion models have enabled the generation of high-quality images, concerns over their potential misuse have also grown. This issue is critical in the…
Distilling Spectral Graph for Object-Context Aware Open-Vocabulary Semantic Segmentation
Chanyoung Kim, Dayun Ju, Woojung Han +2
Open-Vocabulary Semantic Segmentation (OVSS) has advanced with recent vision-language models (VLMs), enabling segmentation beyond predefined categories through various learning sch…
EAGLE: Eigen Aggregation Learning for Object-Centric Unsupervised Semantic Segmentation
Chanyoung Kim, Woojung Han, Dayun Ju +1
Semantic segmentation has innately relied on extensive pixel-level annotated data, leading to the emergence of unsupervised methodologies. Among them, leveraging self-supervised Vi…
Advancing Text-Driven Chest X-Ray Generation with Policy-Based Reinforcement Learning
Woojung Han, Chanyoung Kim, Dayun Ju +2
Recent advances in text-conditioned image generation diffusion models have begun paving the way for new opportunities in modern medical domain, in particular, generating Chest X-ra…
CoBra: Complementary Branch Fusing Class and Semantic Knowledge for Robust Weakly Supervised Semantic Segmentation
Woojung Han, Seil Kang, Kyobin Choo +1
Leveraging semantically precise pseudo masks derived from image-level class knowledge for segmentation, namely image-level Weakly Supervised Semantic Segmentation (WSSS), still rem…