| pipeline_tag: robotics | |
| # GeneralVLA Model Assets | |
| This repository stores pretrained model assets and checkpoints for **GeneralVLA-2: Geometry-Aware Reconstruction and Governed Memory for Robot Planning**. | |
| - **Paper:** [GeneralVLA-2: Geometry-Aware Reconstruction and Governed Memory for Robot Planning](https://huggingface.co/papers/2606.17480) | |
| - **Project Website:** [GeneralVLA-2](https://aigeeksgroup.github.io/GeneralVLA-2/) | |
| - **GitHub Repository:** [AIGeeksGroup/GeneralVLA-2](https://github.com/AIGeeksGroup/GeneralVLA-2) | |
| ## Layout | |
| - `LISA-7B-v1-explanatory/` | |
| - `clip-vit-large-patch14/` | |
| - `segagent/zzzmmz/SegAgent-Model/` | |
| - `sam_vit_h_4b8939.pth` | |
| - `checkpoints/v1/checkpoint-rs.tar` | |
| Please refer to the official [GitHub repository](https://github.com/AIGeeksGroup/GeneralVLA-2) for environment setup, memory VLA runtime configuration, and evaluation benchmarks. | |
| ## Citation | |
| ```bibtex | |
| @article{wang2026generalvla2, | |
| title={GeneralVLA-2: Geometry-Aware Reconstruction and Governed Memory for Robot Planning}, | |
| author={Wang, Haoyu and Ma, Guoqing and Zhang, Zeyu and Guo, Yandong and Shi, Boxin and Tang, Hao}, | |
| journal={arXiv preprint arXiv:2606.17480}, | |
| year={2026} | |
| } | |
| ``` |