3 papers
cs.CV2026
Not all tokens contribute equally to diffusion learning
Guoqing Zhang, Lu Shi, Wanru Xu +4
With the rapid development of conditional diffusion models, significant progress has been made in text-to-video generation. However, we observe that these models often neglect sema…
cs.CV2025
Condition Weaving Meets Expert Modulation: Towards Universal and Controllable Image Generation
Guoqing Zhang, Xingtong Ge, Lu Shi +5
The image-to-image generation task aims to produce controllable images by leveraging conditional inputs and prompt instructions. However, existing methods often train separate cont…
cs.CV2025
Differential Contrastive Training for Gaze Estimation
Lin Zhang, Yi Tian, XiYun Wang +3
The complex application scenarios have raised critical requirements for precise and generalizable gaze estimation methods. Recently, the pre-trained CLIP has achieved remarkable pe…