@article{3dcavlaleveragingdepthand3dcontextto,
  title = {3D CAVLA: Leveraging Depth and 3D Context to Generalize Vision Language Action Models for Unseen Tasks},
  author = {Vineet Bhat and Yu-Hsiang Lan and Prashanth Krishnamurthy and Ramesh Karri and Farshad Khorrami},
  year = {2025},
  eprint = {2505.05800},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2505.05800v1},
}