This repository provides pretrained checkpoints for Vision-and-Language Navigation in Continuous Environments (VLN-CE).

The models are developed based on the V2-VLNCE framework and are trained on standard VLN benchmarks such as Room-to-Room (R2R) and Room-across-Room (RxR). These models learn to follow natural language instructions and navigate in 3D environments using vision-and-language representations.

This release is intended as a checkpoint dump for research use and reproducibility.

The following checkpoints are included:

These checkpoints are stored as raw PyTorch weights.

To properly load and run the model, you need the original training codebase.

Huggingface: https://huggingface.co/papers/2507.08831 ArXiv: https://arxiv.org/abs/2507.08831

Full training and evaluation pipeline is available at:

If you use these models, please cite the corresponding work: