@inproceedings{embodiedsceneunderstandingforvision,
  title = {Embodied Scene Understanding for Vision Language Models via MetaVQA},
  author = {Weizhen Wang and Chenda Duan and Zhenghao Peng and Yuxin Liu and Bolei Zhou},
  year = {2025},
  booktitle = {CVPR 2025 1},
  eprint = {2501.09167},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2501.09167v1},
}