readme init

README.md

@@ -1,3 +1,20 @@
+# MTU3D Checkpoints
+
+[📄 Paper (MTU3D)](https://www.arxiv.org/abs/2507.04047) | [🧾 Project GitHub](https://github.com/MTU3D/MTU3D)
+
+The **MTU3D checkpoints** provides all the checkpoints in the [Move to Understand a 3D Scene: Bridging Visual Grounding and Exploration for Efficient and Versatile Embodied Navigation(ICCV25)](https://www.arxiv.org/abs/2507.04047), including **stage1 pretrain model**, **stage2 pretrain model**, and three navigation dataset specific **stage2 fine-tune models**. 
+
+---
+
+### Citation:
+```
+@article{zhu2025mtu,
+  title = {Move to Understand a 3D Scene: Bridging Visual Grounding and Exploration for Efficient and Versatile Embodied Navigation},
+  author = {Zhu, Ziyu and Wang, Xilin and Li, Yixuan and Zhang, Zhuofan and Ma, Xiaojian and Chen, Yixin and Jia, Baoxiong and Liang, Wei and Yu, Qian and Deng, Zhidong and Huang, Siyuan and Li, Qing},
+  journal = {International Conference on Computer Vision (ICCV)},
+  year = {2025}  
+}
+```
 ---
 license: cc-by-4.0
 ---