Author name: Wenshuo Peng, Gongxuan Wang, Tianmeng Yang, Chuanhao Li, Xiaojie Xu, Hui He, Kaipeng Zhang

arXiv:2512.21507v5 Announce Type: replace
Abstract: Recent text-to-video generation models have made remarkable progress in visual realism, motion fidelity, and text-video alignment, yet they still struggle to produce socially coherent behavior. Unlik…