Skip to content

Conversation

@DuangZhu
Copy link

@DuangZhu DuangZhu commented Dec 31, 2025

PR Description

This PR introduces a new projects/ subfolder under source/en/user_guide/internnav/ to host InternVLA-N1 extensions, such as new models and new benchmarks.

For this PR, the focus is on adding a benchmark. I added benchmark.md under projects/, which provides a detailed guide for using VL-LN Bench, including:

  • additional environment setup beyond InternVLA-N1,
  • data collection pipeline,
  • model training and evaluation on VL-LN Bench.

This structure is intended to make future extensions easier to organize and maintain.

@Tai-Wang Tai-Wang requested a review from kew6688 December 31, 2025 05:54
@kew6688 kew6688 requested a review from Tai-Wang December 31, 2025 08:18
Copy link

@Tai-Wang Tai-Wang left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Modify the dataset names, IGN and IIGN

@@ -0,0 +1,157 @@
# Extended Benchmarks in InternNav

This guide details how to use specific dataset for training a VLA model for different navigation benchmark.

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

benchmarks

# Or directly run
python scripts/eval/eval.py \
--config scripts/eval/configs/habitat_dialog_cfg.py
```

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Add benchmark results. Please follow the readme for each model in mmdet or InternNav readme to add more reference for reimplementing a work.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants