Improving Factuality of 3D Brain MRI Report Generation with Paired Image-domain Retrieval and Text-domain Augmentationby…
Optical-Flow Guided Prompt Optimization for Coherent Video Generationby Hyelin Nam, Jaemin Kim, Dohun Lee, Jong…
IterIS: Iterative Inference-Solving Alignment for LoRA Mergingby Hongxu Chen, Runshi Li, Bowei Zhu, Zhen Wang,…
Text Embedding is Not All You Need: Attention Control for Text-to-Image Semantic Alignment with Text…
Reward Fine-Tuning Two-Step Diffusion Models via Learning Differentiable Latent-Space Surrogate Rewardby Zhiwei Jia, Yuesong Nan,…
Derivative-Free Diffusion Manifold-Constrained Gradient for Unified XAIby Won Jun Kim, Hyungjin Chung, Jaemin Kim, Sangmin…
Adaptively Controllable Diffusion Model for Efficient Conditional Image Generationby Yucheng Xing, Xiaodong Liu, Xin WangFirst…
OminiControl: Minimal and Universal Control for Diffusion Transformerby Zhenxiong Tan, Songhua Liu, Xingyi Yang, Qiaochu…
Efficient Pruning of Text-to-Image Models: Insights from Pruning Stable Diffusionby Samarth N Ramesh, Zhixue ZhaoFirst…
HeadRouter: A Training-free Image Editing Framework for MM-DiTs by Adaptively Routing Attention Headsby Yu Xu,…