@article{evo0visionlanguageactionmodelwithimplici,
  title = {Evo-0: Vision-Language-Action Model with Implicit Spatial Understanding},
  author = {Tao Lin and Gen Li and Yilei Zhong and Yanwen Zou and Yuxin Du and Jiting Liu and Encheng Gu and Bo Zhao},
  year = {2025},
  eprint = {2507.00416},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2507.00416},
}