@article{clutterrobustvisionlanguageactionmodelst,
  title = {Clutter-Robust Vision-Language-Action Models through Object-Centric and Geometry Grounding},
  author = {Khoa Vo and Taisei Hanyu and Yuki Ikebe and Trong Thang Pham and Nhat Chung and Minh Nhat Vu and Duy Nguyen Ho Minh and Anh Nguyen and Anthony Gunderman and Chase Rainwater and Ngan Le},
  year = {2025},
  eprint = {2512.22519},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2512.22519},
}