@article{vlgavisionlanguagegeometryactionmodelsfo,
  title = {VLGA: Vision-Language-Geometry-Action Models for Autonomous Driving},
  author = {Jin Yao and Dhruva Dixith Kurra and Tom Lampo and Zezhou Cheng and Danhua Guo and Burhan Yaman},
  year = {2026},
  eprint = {2606.12396},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2606.12396},
}