2D or 3D: Who Governs Salience in VLA Models? -- Tri-Stage Token Pruning Framework with Modality Salience Awareness

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zheng, Zihao, Tian, Sicheng, Mao, Zhihao, Zhang, Lingyue, Li, Chenyue, Zhang, Ziyun, Gao, Hong, Huang, Yuchen, Xu, Yutong, Luo, Guojie, Chen, Xiang
Format:	Preprint
Published:	2026
Subjects:	Multimedia Computer Vision and Pattern Recognition Robotics
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2604.09244