| # Embodied-R Model Weights |
|
|
| This repository contains the RL-trained weights of the model introduced in the paper: |
| **[Embodied-R: Collaborative Framework for Activating Embodied Spatial Reasoning in Foundation Models via Reinforcement Learning]**. |
|
|
| For more details about the model and its implementation, please refer to the GitHub repository: |
| [https://github.com/EmbodiedCity/Embodied-R.code](https://github.com/EmbodiedCity/Embodied-R.code). |
|
|
| ## Citation |
| If this work has contributed to your research, welcome to cite it: |
|
|
| ``` |
| @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} |
| } |
| ``` |
| --- |
| license: mit |
| --- |
|
|
