12 papers
ContrastiveCFG: Guiding Diffusion Sampling by Contrasting Positive and Negative Concepts
Jinho Chang, Changsun Lee, Hyungjin Chung +1
As Classifier-Free Guidance (CFG) has proven effective in conditional diffusion model sampling for improved condition alignment, many applications use a negated CFG term as a Negat…
InverseCrafter: Efficient Video ReCapture as a Latent Domain Inverse Problem
Yeobin Hong, Suhyeon Lee, Hyungjin Chung +1
Recent approaches in controllable novel view video generation often rely on fine-tuning pre-trained Video Diffusion Models (VDMs). This dominant paradigm is computationally expensi…
Accelerating Video Inverse Problem Solvers with Autoregressive Diffusion Models
Taesung Kwon, Jonghyun Park, Hyungjin Chung +1
Diffusion models provide powerful priors for zero-shot video inverse problems, but their real-time deployment is hindered by two inefficiencies: high initial latency caused by holi…
Stitched Value Model for Diffusion Alignment
Hyojun Go, Hyungjin Chung, Prune Truong +8
For practical use, diffusion- or flow-based generative models must be aligned with task-specific rewards, such as prompt fidelity or aesthetic preference. That alignment is challen…
EditCrafter: Tuning-free High-Resolution Image Editing via Pretrained Diffusion Model
Kunho Kim, Sumin Seo, Yongjun Cho +1
We propose EditCrafter, a high-resolution image editing method that operates without tuning, leveraging pretrained text-to-image (T2I) diffusion models to process images at resolut…
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…