One Token Per Frame: Reconsidering Visual Bandwidth in World Models for VLA Policy

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Tang, Zuojin, Yuan, Shengchao, Bai, Xiaoxin, Jing, Zhiyuan, Ma, De, Pan, Gang, Liu, Bin
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/2605.07931