diff --git a/README.md b/README.md
index 0c37315..29577e2 100644
--- a/README.md
+++ b/README.md
@@ -63,7 +63,7 @@ In our experiments, we consider the following three opensource dataset:
 |Z1_DualArm_StackBox|[Unitree Z1](https://www.unitree.com/z1)|[Huggingface](https://huggingface.co/datasets/unitreerobotics/Z1_Dual_Dex1_StackBox_Dataset/tree/v2.1)|
 |Z1_DualArm_StackBox_V2|[Unitree Z1](https://www.unitree.com/z1)|[Huggingface](https://huggingface.co/datasets/unitreerobotics/Z1_Dual_Dex1_StackBox_Dataset_V2/tree/v2.1)|
 |Z1_DualArm_Cleanup_Pencils|[Unitree Z1](https://www.unitree.com/z1)|[Huggingface](https://huggingface.co/datasets/unitreerobotics/Z1_Dual_Dex1_CleanupPencils_Dataset/tree/v2.1)|
-|G1_Pack_Camera|[Unitree G1](https://huggingface.co/datasets/unitreerobotics/G1_Dex1_MountCameraRedGripper_Dataset/tree/v2.1)
+|G1_Pack_Camera|[Unitree G1](https://www.unitree.com/g1)|[Huggingface](https://huggingface.co/datasets/unitreerobotics/G1_Dex1_MountCameraRedGripper_Dataset/tree/v2.1)|
 
 To train on your own dataset, first to have the data following the [Huggingface LeRobot V2.1](https://github.com/huggingface/lerobot) dataset format. Assume the dataset’s source directory structure is as follows:
 ```