| --- |
| language: en |
| license: mit |
| base_model: openvla/openvla-7b |
| base_model_relation: adapter |
| tags: |
| - robotics |
| - vision-language-action |
| - residual-adapter |
| - bas-vla |
| - arxiv:2609.23650 |
| --- |
| |
| # BAS-VLA: OpenVLA residual adapter |
|
|
| [Paper](https://arxiv.org/abs/2609.23650) · [Project](https://nebulis-lab.com/BAS-VLA/) · [Code](https://github.com/NEBULIS-Lab/BAS-VLA) |
|
|
| This release provides a trained text-conditioned residual adapter and matched inputs for the **OpenVLA / LIBERO-10 offline action-calibration setting**, a selected subset of the settings studied in *Beyond Appearance Shifts: Task-Semantic Action Calibration for VLA Models*. |
|
|
| Each record pairs a shared observation with clean, task-preserving, and semantics-changing instructions and their frozen-carrier actions. The included cases cover target-object and executability-condition changes. The adapter applies a bounded action correction using the base action and binary bag-of-words instruction features. |
|
|
| ## Files |
|
|
| | Location | Contents | |
| | --- | --- | |
| | `adapter/` | Trained residual weights, vocabulary, and loading/action metadata | |
| | `data/triplets.json` | Matched action triplets, expert actions, and demonstration-level train/validation/test assignments | |
| | `data/observations.npz` | Source agent-view RGB images aligned with the records | |
| | `data/states/` | Sampled simulator states and source demonstration initial states | |
| | `data/scenes/` | The corresponding LIBERO BDDL scenes | |
| | `data/cases.json`, `data/manifest.json` | Instruction triplets, source references, array alignment, and input preprocessing | |
| | `normalization/` | Action statistics used to construct the frozen OpenVLA actions and their source information | |
| | `training_config.json`, `offline_metrics.json` | Training objective configuration and offline evaluation summaries | |
| | `example.py` | CPU example applying the adapter to a supplied record | |
|
|
| ## Download and use |
|
|
| Install the [BAS-VLA code](https://github.com/NEBULIS-Lab/BAS-VLA) and its dependencies, then download the files: |
|
|
| ```python |
| from huggingface_hub import snapshot_download |
| |
| snapshot_download("Shuaijun/BAS-VLA", local_dir="artifacts/bas-vla") |
| ``` |
|
|
| Run the included example from the directory containing `artifacts/`: |
|
|
| ```bash |
| python artifacts/bas-vla/example.py |
| ``` |
|
|
| The example loads the adapter on CPU and prints calibrated clean, control, and changed-instruction actions for a held-out record. Use `--record-index` to select another record. |
|
|
| ## Action and feature conventions |
|
|
| Use the exact contract in `adapter/adapter_metadata.json` when supplying new actions. The carrier is `openvla/openvla-7b`; the cached actions use the bundled `libero_10_no_noops` statistics from `moojink/openvla-7b-oft-finetuned-libero-10`, followed by the documented gripper transform. Instructions use the supplied binary bag-of-words vocabulary. |
|
|
| The checkpoint's action-space identifier is `openvla_libero10_unnormalized_sign_gripper_offline`. The code repository's OpenPI and OpenVLA-OFT rollout runners require adapters matched to their own carrier and action conventions. Load this checkpoint through the supplied example or the `ResidualAdapter` class with the recorded convention. |
|
|
| `data/manifest.json` explains how RGB arrays, simulator states, scene files, and demonstration frames align. LIBERO supplies the scene assets and simulator. Base VLA weights are obtained separately from their upstream model repositories. |
|
|
| ## Sources and license |
|
|
| BAS-VLA contributions are released under the MIT License. The included LIBERO-derived data and OpenVLA-OFT normalization statistics retain their upstream MIT notices. See [NOTICE.md](NOTICE.md) and `licenses/` for the source links and notices. |
|
|
| ## Citation |
|
|
| ```bibtex |
| @inproceedings{liu2026basvla, |
| title = {Beyond Appearance Shifts: Task-Semantic Action Calibration for VLA Models}, |
| author = {Liu, Shuaijun and You, Feiyang and Wu, Chengyu and Hao, Shuyang and Zhang, Chenglong and Cai, Jingyao and Chen, Xingwei and Sun, Li and Su, Ningxin}, |
| booktitle = {Advances in Neural Information Processing Systems}, |
| year = {2026}, |
| url = {https://arxiv.org/abs/2609.23650} |
| } |
| ``` |
|
|
