@inproceedings{10.1145/3746027.3755703,
  author = {Zhao, Baining and Wang, Ziyou and Fang, Jianjie and Gao, Chen and Man, Fanhang and Cui, Jinqiang and Wang, Xin and Chen, Xinlei and Li, Yong and Zhu, Wenwu},
  title = {Embodied-R: Collaborative Framework for Activating Embodied Spatial Reasoning in Foundation Models via Reinforcement Learning},
  year = {2025},
  isbn = {9798400720352},
  publisher = {Association for Computing Machinery},
  address = {New York, NY, USA},
  url = {https://doi.org/10.1145/3746027.3755703},
  doi = {10.1145/3746027.3755703},
  booktitle = {Proceedings of the 33rd ACM International Conference on Multimedia},
  pages = {11071–11080},
  numpages = {10},
  keywords = {embodied intelligence, reasoning, vision-language model},
  location = {Dublin, Ireland},
  series = {MM '25}
}