5 papers
Learning to Be Guided: Shaping Latent Geometry for Classifier-Free Guidance
Haoming Liu, Junhao Zhu, Shaoyi Zheng +4
Classifier-free guidance (CFG) is a standard component of conditional diffusion models, and guided generation performance has become the \textit{de facto} measure of state-of-the-a…
Histogram-constrained Image Generation
Haoming Liu, Yuanhe Guo, Yijia Cao +2
Diffusion models have emerged as a dominant paradigm in generative modeling, enabling high-fidelity sampling from complex data distributions. Despite impressive capabilities, contr…
From Navigation to Refinement: Revealing the Two-Stage Nature of Flow-based Diffusion Models through Oracle Velocity
Haoming Liu, Jinnuo Liu, Yanhao Li +5
Flow-based diffusion models have emerged as a leading paradigm for training generative models across images and videos. However, their memorization-generalization behavior remains…
HilbertA: Hilbert Attention for Image Generation with Diffusion Models
Shaoyi Zheng, Wenbo Lu, Yuxuan Xia +2
Designing sparse attention for diffusion transformers requires reconciling two-dimensional spatial locality with GPU efficiency, a trade-off that current methods struggle to achiev…
Boosting Few-Shot Segmentation via Instance-Aware Data Augmentation and Local Consensus Guided Cross Attention
Li Guo, Haoming Liu, Yuxuan Xia +2
Few-shot segmentation aims to train a segmentation model that can fast adapt to a novel task for which only a few annotated images are provided. Most recent models have adopted a p…