@article{motionvlavisionlanguageactionmodelforhum,
  title = {MotionVLA: Vision-Language-Action Model for Humanoid Motion},
  author = {Nonghai Zhang and Siyu Zhai and Yanjun Li and Zeyu Zhang and Zhihan Yin and Yandong Guo and Boxin Shi and Hao Tang},
  year = {2026},
  eprint = {2606.15142},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2606.15142},
}