UniD3: unified discrete diffusion for simultaneous vision-language generation

• Main Authors: Hu, Minghui, Zheng, Chuanxia, Cham, Tat-Jen, Suganthan, Ponnuthurai Nagaratnam, Yang, Zuopeng, Zheng, Heliang, Wang, Chaoyue, Tao, Dacheng
• 其他作者: School of Computer Science and Engineering
• 格式: Conference or Workshop Item
• 語言: English
• 出版: 2023
• 主題: Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision; Diffusion; Computer Graphics
• 在線閱讀: https://hdl.handle.net/10356/172665; https://openreview.net/forum?id=8JqINxA-2a
• 機構: Nanyang Technological University

The recently developed discrete diffusion model performs extraordinarily well in generation tasks, especially in the text-to-image task, showing great potential for modeling multimodal signals. In this paper, we leverage these properties and present a unified multimodal generation model, which can p...