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
Intrinsic Logit-Based Debiasing (ILBD), a robust post-hoc framework that estimates bias directly from task-relevant data without external dependencies and class priors, and effectively rectifies the classifier's bias directly from the inherent statistical patterns of the training data.