@article{mantisaversatilevisionlanguageactionmode,
  title = {Mantis: A Versatile Vision-Language-Action Model with Disentangled Visual Foresight},
  author = {Yi Yang and Xueqi Li and Yiyang Chen and Jin Song and Yihan Wang and Zipeng Xiao and Jiadi Su and You Qiaoben and Pengfei Liu and Zhijie Deng},
  year = {2025},
  eprint = {2511.16175},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2511.16175},
}