DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledge

@misc{jin2025dreamvlavisionlanguageactionmodel,
      title={DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledge},
      author={Xin Jin and Wenyao Zhang and Wenjun Zeng and Yunnan Wang and He Wang and Jiazhao Zhang and Zhizheng Zhang and Li Yi and Runpei Dong and Zekun Qi and Jiawei He and Hongsi Liu and XinQiang Yu},
      year={2025},
      eprint={2507.04447},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2507.04447},
}