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…
Universal Reasoner: A Single, Composable Plug-and-Play Reasoner for Frozen LLMs
Jaemin Kim, Hangeol Chang, Hyunmin Hwang +2
Large Language Models (LLMs) have demonstrated remarkable general capabilities, but enhancing skills such as reasoning often demands substantial computational resources and may com…
Training-Free Reward-Guided Image Editing via Trajectory Optimal Control
Jinho Chang, Jaemin Kim, Jong Chul Ye
Recent advancements in diffusion and flow-matching models have demonstrated remarkable capabilities in high-fidelity image synthesis. A prominent line of research involves reward-g…
ReDirector: Creating Any-Length Video Retakes with Rotary Camera Encoding
Byeongjun Park, Byung-Hoon Kim, Hyungjin Chung +1
We present ReDirector, a novel camera-controlled video retake generation method for dynamically captured variable-length videos. In particular, we rectify a common misuse of RoPE i…
InvFusion: Bridging Supervised and Zero-shot Diffusion for Inverse Problems
Noam Elata, Hyungjin Chung, Jong Chul Ye +2
Diffusion Models have demonstrated remarkable capabilities in handling inverse problems, offering high-quality posterior-sampling-based solutions. Despite significant advances, a f…