Downloads · 30 days
0
Uni-NaVid
Jzzhang/Uni-NaVid
Uni-NaVid is a machine learning model from Jzzhang. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Pretrained Weights of Uni-NaVid: A Video-based Vision-Language-Action Model for Unifying Embodied Navigation Tasks (RSS 2025)
Access
Public
Updated Oct 15, 2025
Repo size
32.5 GB
Likes
8
Public
Repo makeup
Click a slice to open those files.
.bin15.5 GB · 95%
At a glance
- Access
- Public
- Created
- Oct 13, 2025
- Updated
- Oct 15, 2025
- SHA
- 04372225
Model card
From the Hugging Face model README
Pretrained Weights of Uni-NaVid: A Video-based Vision-Language-Action Model for Unifying Embodied Navigation Tasks (RSS 2025)
Paper: https://arxiv.org/pdf/2412.06224
The model is trained on samples collected from the training splits of VLN-CE R2R and RxR, EVT-Bench, ObjectNav, EQA.
| Evaliation Benchmark | TL | NE | OS | SR | SPL |
|---|---|---|---|---|---|
| VLN-CE R2R Val. | 9.22 | 4.96 | 57.4 | 51.8 | 47.7 |
| VLN-CE RxR Val. | 18.4 | 5.67 | 64.4 | 66.4 | 44.5 |
The related inference code can be found in here
- Created
- Oct 13, 2025
- Updated
- Oct 15, 2025