World Guidance: World Modeling in Condition Space for Action Generation

作者：Yue Su, Sijin Chen, Haixin Shi, Mingyu Liu, Zhengshen Zhang, Ningyuan Huang, Weiheng Zhong, Zhengbang Zhu, Yuxiao Liu, Xihui Liu · 单位：ByteDance Seed, The University of Hong Kong · 会议/期刊：arXiv · 日期：2026-02-25 · 来源：Low-Level Learning-Based Action Modelling / Input Modelling / 2D Vision Language Action Models with Auxiliary Tasks - World Model & Visual Prediction / Visual/State Prediction/Generation