@misc{liang2026depstatejepa,
  title = {DepState-JEPA: Learning Depth-Grounded
    State Representation for Visual Perception
    and Manipulation},
  author = {Liang, Xiujian and Na, Liuyuan and
    Du, Zehao and Xu, Jiacheng and Song, Weixi and
    Sun, Mingyang and Ma, Xingjun and Lu, Cewu and
    Sun, Jianhua},
  year = {2026},
  eprint        = {2610.29246},
  archivePrefix = {arXiv},
  primaryClass  = {cs.RO},
  url           = {https://arxiv.org/abs/2610.29246}
}