Generative Multimodal Pretraining with Discrete Diffusion Timestep Tokens

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Pan, Kaihang, Lin, Wang, Yue, Zhongqi, Ao, Tenglong, Jia, Liyu, Zhao, Wei, Li, Juncheng, Tang, Siliang, Zhang, Hanwang
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2504.14666