How Long Can Unified Multimodal Models Generate Images Reliably? Taming Long-Horizon Interleaved Image Generation via Context Curation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Chen, Haoyu, Liu, Qing, Zhou, Yuqian, Zhang, He, Wang, Zhaowen, Ren, Mengwei, Ren, Jingjing, Wang, Xiang, Lin, Zhe, Zhu, Lei
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2603.07540