@article{endovladualphasevisionlanguageaction,
  title = {EndoVLA: Dual-Phase Vision-Language-Action Model for Autonomous Tracking in Endoscopy},
  author = {Chi Kit Ng and Long Bai and Guankun Wang and Yupeng Wang and Huxin Gao and Kun Yuan and Chenhan Jin and Tieyong Zeng and Hongliang Ren},
  year = {2025},
  eprint = {2505.15206},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2505.15206v1},
}