| license: gpl-3.0 | |
| pipeline_tag: robotics | |
| library_name: pytorch | |
| # ManipTrans: Efficient Dexterous Bimanual Manipulation Transfer via Residual Learning | |
| [](https://arxiv.org/abs/2503.21860) | |
| [](https://maniptrans.github.io/) | |
| [![Dataset (uploading)]](https://img.shields.io/badge/Dataset%20(uploading)-orange?style=for-the-badge&labelColor=FFD21E&color=FFD21E) | |
| This model is described in the paper [ManipTrans: Efficient Dexterous Bimanual Manipulation Transfer via Residual Learning](https://huggingface.co/papers/2503.21860). It's a two-stage method for efficiently transferring human bimanual skills to dexterous robotic hands in simulation. The model first pre-trains a generalist trajectory imitator and then fine-tunes a specific residual module. | |
| For code and usage instructions please see the project's Github repository: [ManipTrans](https://github.com/ManipTrans/ManipTrans). |