3 papers
cs.CV2026
Residual-Stream Burden Shapes Representation Learning in Diffusion Transformers
Tongtong Liang, Siqi Kou, Ziqiao Xi +6
In diffusion-based generation, a neural network can be trained to predict the clean data, the noise, or the velocity from a noisy input. These prediction targets are interconvertib…
cs.CV2025
AttentionDrag: Exploiting Latent Correlation Knowledge in Pre-trained Diffusion Models for Image Editing
Biao Yang, Muqi Huang, Yuhui Zhang +8
Traditional point-based image editing methods rely on iterative latent optimization or geometric transformations, which are either inefficient in their processing or fail to captur…
cs.CV2025
A 2D Semantic-Aware Position Encoding for Vision Transformers
Xi Chen, Shiyang Zhou, Muqi Huang +9
Vision transformers have demonstrated significant advantages in computer vision tasks due to their ability to capture long-range dependencies and contextual relationships through s…