7 papers · 1 filter
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…
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…
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…