@article{improvingvisionlanguageactionmodelfinetu,
  title = {Improving Vision-Language-Action Model Fine-Tuning with Structured Stage and Keyframe Supervision},
  author = {Yuan Xu and Yixiang Chen and Kai Wang and Jiabing Yang and Peiyan Li and Qisen Ma and Yan Huang and Liang Wang},
  year = {2026},
  eprint = {2606.26801},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2606.26801},
}