| library_name: pytorch | |
| license: apache-2.0 | |
| pipeline_tag: robotics | |
| tags: | |
| - robotics | |
| - vision-language-action | |
| - vla | |
| - qwen3-vl | |
| - rhinovla | |
| - checkpoint | |
| # RhinoVLA 预训练权重 | |
| 本仓库仅提供 RhinoVLA 预训练权重： | |
| - `rhinovla_pretrain.ckpt` | |
| ## 资源 | |
| - 模型仓库：[Hugging Face](https://huggingface.co/HuixiAI/RhinoVLA) | [ModelScope](https://www.modelscope.cn/models/HuixiAI/RhinoVLA) | |
| - 代码与微调：[GitHub](https://github.com/HuixiAI/RhinoVLA) | |
| - 技术报告：[Hugging Face Papers](https://huggingface.co/papers/2606.07383) | [ModelScope Papers](https://www.modelscope.cn/papers/2606.07383/aiRead) | [arXiv](https://arxiv.org/abs/2606.07383) | |
| ## Citation | |
| ```bibtex | |
| @misc{intelligence2026rhinovlatechnicalreport, | |
| title={RhinoVLA Technical Report}, | |
| author={Huixi Intelligence and Chen Zhang and Chenyang Zhou and Guanglei Ding and Guanghui He and Haibin Gao and Jiajia Chen and Jianyong Zhang and Lianyi Yu and Ningyi Xu and Ping Xu and Qingchen Li and Yingjun Hu and Yijia Zhang and Yuxi Liu}, | |
| year={2026}, | |
| eprint={2606.07383}, | |
| archivePrefix={arXiv}, | |
| primaryClass={cs.RO}, | |
| url={https://arxiv.org/abs/2606.07383}, | |
| } | |
| ``` | |