@article{vlmqlearningaligningvisionlanguage,
  title = {VLM Q-Learning: Aligning Vision-Language Models for Interactive Decision-Making},
  author = {Jake Grigsby and Yuke Zhu and Michael Ryoo and Juan Carlos Niebles},
  year = {2025},
  eprint = {2505.03181},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2505.03181v1},
}