C^2ROPE: Causal Continuous Rotary Positional Encoding for 3D Large Multimodal-Models Reasoning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Ye, Guanting, Zhao, Qiyan, Yu, Wenhao, Zhang, Xiaofeng, Ji, Jianmin, Zhang, Yanyong, Yuen, Ka-Veng
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/2602.10551