Mantis: A Versatile Vision-Language-Action Model with Disentangled Visual Foresight

作者：Yi Yang, Xueqi Li, Yiyang Chen, Jin Song, Yihan Wang, Zipeng Xiao, Jiadi Su, You Qiaoben, Pengfei Liu, Zhijie Deng, SJTU SII SUSTech NJUPT FDU BOSCH · 单位：Lab/Mantis 220k Human · 会议/期刊：arXiv · 日期：2025-11-20 · 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