ProWorld is introduced, a world model that jointly predicts multi-view video and robot state, then feeds both back to a frozen policy for repeated interaction, supporting joint visual-proprioceptive feedback and failure-aware training as a basis for world-model-based policy evaluation.
Zi-Jun Wang, Tian-Yi Yan, Hao-Kun Lin et al.· 0 citations
EWAM is an action-centric unified embodied model whose asymmetric joint attention lets action tokens read semantic, current-visual, predicted-future, and action information at every layer while the perceptual experts retain their distinct roles, suggesting that unified embodied learning can induce an ordered internal p...
Hao Wang, Jia-Jun Wen, Jing-Zhi Liu et al.· arXiv.org· 1 citation
PAVXploreRL is a reinforcement learning framework built on a pretrained latent world model that explicitly optimizes PAV objectives through reward-driven training, and jointly leverages ID trajectories and noise-driven OOD action exploration, without paired video supervision.