README.md

---
license: mit
datasets:
- rjgpinel/GEMBench
- rjgpinel/RLBench-18Task
pipeline_tag: robotics
---

## Official 3D-LOTUS/3D-LOTUS++ Code Repository

You can find our code and the corresponding instructions to run our model at: https://github.com/vlc-robot/robot-3dlotus.

## Citation

If you use our 3D-LOTUS/3D-LOTUS++ model, please kindly cite our [work](https://arxiv.org/abs/2410.01345):

**BibTeX:**

```bibtex
 @inproceedings{garcia25gembench,
    author    = {Ricardo Garcia and Shizhe Chen and Cordelia Schmid},
    title     = {Towards Generalizable Vision-Language Robotic Manipulation: A Benchmark and LLM-guided 3D Policy},
    booktitle = {IEEE International Conference on Robotics and Automation (ICRA)},
    year      = {2025}
}
```