Geometry-Aware Rotary Position Embedding for Consistent Video World Model

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Xiang, Chendong, Liu, Jiajun, Zhang, Jintao, Yang, Xiao, Fang, Zhengwei, Wang, Shizun, Wang, Zijun, Zou, Yingtian, Su, Hang, Zhu, Jun
Format:	Preprint
Published:	2026
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/2602.07854