---
license: mit
language:
- en
base_model:
- openvla/openvla-7b
pipeline_tag: robotics
---
# Model Card for hifvla-libero-object 
HiF-VLA: Hindsight, Insight and Foresight through Motion Representation for Vision-Language-Action Models.
- arXiv: [https://arxiv.org/abs/2512.09928](https://arxiv.org/abs/2512.09928)
- 💬 Project page: [https://hifvla.github.io/](https://hifvla.github.io/)
- 🖥️ Dataset: [https://huggingface.co/datasets/minnielin/libero_trajid_rlds](https://huggingface.co/datasets/minnielin/libero_trajid_rlds)
- Github: [https://github.com/OpenHelix-Team/HiF-VLA](https://github.com/OpenHelix-Team/HiF-VLA)

## Citation instructions

```BibTeX
@misc{lin2025hifvlahindsightinsightforesight,
      title={HiF-VLA: Hindsight, Insight and Foresight through Motion Representation for Vision-Language-Action Models}, 
      author={Minghui Lin and Pengxiang Ding and Shu Wang and Zifeng Zhuang and Yang Liu and Xinyang Tong and Wenxuan Song and Shangke Lyu and Siteng Huang and Donglin Wang},
      year={2025},
      eprint={2512.09928},
      archivePrefix={arXiv},
      primaryClass={cs.RO},
      url={https://arxiv.org/abs/2512.09928}, 
}
```