Cross-Attention Head Position Patterns Can Align with Human Visual Concepts in Text-to-Image Generative Modelsby Jungwon…
Long Video Diffusion Generation with Segmented Cross-Attention and Content-Rich Video Data Curationby Xin Yan, Yuxuan…
InstantSwap: Fast Customized Concept Swapping across Sharp Shape Differencesby Chenyang Zhu, Kai Li, Yue Ma,…
FreeCond: Free Lunch in the Input Conditions of Text-Guided Inpaintingby Teng-Fang Hsiao, Bo-Kai Ruan, Sung-Lin…
FollowGen: A Scaled Noise Conditional Diffusion Model for Car-Following Trajectory Predictionby Junwei You, Rui Gan,…
TP-UNet: Temporal Prompt Guided UNet for Medical Image Segmentationby Ranmin Wang, Limin Zhuang, Hongkun Chen,…
Enhancing Financial Domain Adaptation of Language Models via Model Augmentationby Kota Tanabe, Masanori Hirano, Kazuki…
PerceiverS: A Multi-Scale Perceiver with Effective Segmentation for Long-Term Expressive Symbolic Music Generationby Yungang Yi,…
Token Merging for Training-Free Semantic Binding in Text-to-Image Synthesisby Taihang Hu, Linxuan Li, Joost van…
DiMSUM: Diffusion Mamba – A Scalable and Unified Spatial-Frequency Method for Image Generationby Hao Phung,…