GN-BAE-VLN-CE

GN-BAE-VLN-CE is a companion checkpoint for GN0, prepared for Vision-and-Language Navigation in Continuous Environments (VLN-CE) style workflows.

GN0 is a unified research framework for Generation, Evaluation, and Policy Learning in Vision-and-Language Navigation. It connects 3D Gaussian Splatting-based scene construction, high-fidelity embodied simulation, and navigation policy evaluation in visually grounded indoor environments.

This repository provides a GN-BAE checkpoint variant intended to be used with GN0-related VLN-CE / GN-Bench evaluation code.

Intended Use

This model is intended for research on embodied AI and Vision-and-Language Navigation, especially experiments that use GN0 together with VLN-CE style navigation agents or evaluation pipelines.

Use this checkpoint together with the GN0 codebase:

• Code: https://github.com/TeleHuman/GN0
• Project page: https://telehuman-gn0.github.io/
• Paper: https://arxiv.org/abs/2606.03682
• Main GN-BAE checkpoint: https://huggingface.co/TeleEmbodied/GN-BAE

GN0 Context

GN0 consists of three connected components:

Component	Description
GN-Matrix	Large-scale 3DGS navigation data with dynamic human avatars.
GN-Bench	Interactive benchmark and simulator for high-fidelity VLN evaluation.
GN-BAE	Navigation foundation model for map-based and map-free policy learning.

GN-BAE-VLN-CE is released as part of this GN0 model ecosystem.

Usage

Please follow the setup instructions in the GN0 repository. A typical workspace includes VLN_CE, GN-Bench-Tools, datasets, and model checkpoints:

GN0
├── data
│   ├── datasets
│   │   └── GN_Matrix
│   │       └── InteriorGS_episode
│   └── scene_datasets
│       └── InteriorGS
├── GN-Bench-Tools
├── model_zoo
│   └── bae
├── VLN_CE
├── run.py
└── eval_bae_InteriorGS.sh

Place or reference this checkpoint according to the model path expected by your VLN-CE / GN0 evaluation script.

For the GN-Bench InteriorGS evaluation workflow, GN0 shows the following command pattern:

zsh eval_bae_InteriorGS.sh \
  --model-path model_zoo/bae \
  --chunks 1 \
  --procs-per-gpu 1 \
  --save-path tmp/bae_eval

Monitor evaluation progress:

watch -n 1 python analyze_results.py --path tmp/bae_eval

Evaluation

GN0 reports standard VLN metrics from JSON evaluation logs:

Metric	Meaning
TL	Average trajectory length
NE ↓	Navigation error
OS ↑	Oracle success
SR ↑	Success rate
SPL ↑	Success weighted by path length

Please refer to the GN0 repository for dataset preparation, simulator setup, and full evaluation details.

License

This model is released under the Creative Commons Attribution-NonCommercial 4.0 International license (CC BY-NC 4.0).

Citation

If GN0, GN-Bench, or this model is useful for your research, please cite:

@article{li2026gn0,
  title={GN0: Toward a Unified Paradigm for Generation, Evaluation, and Policy Learning in Visual-Language Navigation},
  author={Li, Xinhai and Zhang, Xiaotao and Huang, Yuehao and Dong, Jiankun and Wang, Tianhang and Zhou, Sunyao and Wu, Yunzi and Sun, Chengnuo and Ge, Yunfei and Weng, Qizhen and Zhang, Chi and Bai, Chenjia and Li, Xuelong},
  journal={arXiv preprint arXiv:2606.03682},
  year={2026}
}

Acknowledgements

GN-Bench-Tools is adapted from Habitat-Lab and customized for 3D Gaussian Splatting-based navigation. We thank the Habitat-Lab developers, the InteriorGS authors, and the broader Embodied AI and 3DGS open-source communities.