InstructVLA: Vision-Language-Action Instruction Tuning from Understanding to Manipulation

@misc{yang2025instructvla,
  title = {InstructVLA: Vision-Language-Action Instruction Tuning from Understanding to Manipulation},
  author = {Shuai Yang and Hao Li and Yilun Chen and Bin Wang and Yang Tian and Tai Wang and Han-Qing Wang and Feng Zhao and Yiyi Liao and Jiangmiao Pang},
  year = {2025},
  eprint = {2507.17520},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2507.17520},
}