---
license: mit
pipeline_tag: robotics
tags:
- robotics
- vision-language-action
- vla
- diffusion-policy
- imitation-learning
- ensemble-learning
- robotwin
library_name: pytorch
---

# EnsembleVLA — Released Checkpoints

Released checkpoints for **EnsembleVLA: Ensemble Learning for Vision-Language
Action Models**.

- 💻 **Code:** https://github.com/MingC715/EnsembleVLA
- 📄 **Paper:** ICML 2026 (coming soon)

EnsembleVLA is an energy-based framework for principled composition of diverse
Vision-Language-Action (VLA) policies. It formulates diffusion-based and
flow-based VLA models under a unified energy perspective, where additive energy
aggregation induces policy composition at the distribution level. Multiple
pretrained policies stay **frozen** while a lightweight ensemble head with
learnable composition weights and confidence-aware gating aggregates them into a
stronger policy, evaluated on the RoboTwin2 rollout interface.

## What's in this repository

Two released composition families, each over 8 RoboTwin2 tasks. For every task we
release the lightweight **ensemble head** plus the two **frozen base policies**:

| Family | Base policy 1 | Base policy 2 |
| --- | --- | --- |
| `dp+dp3` | Diffusion Policy (DP) | 3D Diffusion Policy (DP3) |
| `dp+pi0.5` | Diffusion Policy (DP) | pi0.5 / openpi |

**Tasks:** `beat_block_hammer`, `click_alarmclock`, `dump_bin_bigbin`,
`handover_block`, `move_playingcard_away`, `open_laptop`, `place_bread_skillet`,
`stack_bowls_three`.

## Repository layout

Files live at the repository root and mirror the code's `best_checkpoint/` layout:

```text
dp+dp3/<task>/
  ensemble_checkpoint/best.pt          # lightweight EnsembleVLA head
  base_dp/<ckpt>.ckpt                  # frozen DP base policy
  base_dp3/<ckpt>.ckpt                 # frozen DP3 base policy
dp+pi0.5/<task>/
  ensemble_checkpoint/best.pt          # lightweight EnsembleVLA head
  base_dp/<ckpt>.ckpt                  # frozen DP base policy
  base_pi05_checkpoint_dir/
    model.safetensors                  # frozen pi0.5 base policy weights
    metadata.pt
    assets/<task>/norm_stats.json
```

> The pi0.5 base needs all three of `model.safetensors`, `metadata.pt`, and
> `assets/` from the same `base_pi05_checkpoint_dir/`.

## Download

Download everything straight into the code repo's `best_checkpoint/` directory:

```bash
pip install -U huggingface_hub
huggingface-cli download mingchens/EnsembleVLA --repo-type model --local-dir best_checkpoint
```

Then follow the **Environment Setup** and **Evaluation** instructions in the
[GitHub README](https://github.com/MingC715/EnsembleVLA). Only inference
checkpoints are required for evaluation; optimizer states and training/rollout
logs are not included. The full checkpoint manifest (per-task base checkpoints
and results) is in
[`docs/checkpoints.md`](https://github.com/MingC715/EnsembleVLA/blob/main/docs/checkpoints.md).

## License

Released under the [MIT License](https://github.com/MingC715/EnsembleVLA/blob/main/LICENSE).

## Citation

```bibtex
@inproceedings{song2026ensemblevla,
  title={EnsembleVLA: Ensemble Learning for Vision-Language Action Models},
  author={Song, Mingchen and Deng, Xiang and Wei, Jie and Jiang, Dongmei and Nie, Liqiang and Guan, Weili},
  booktitle={International Conference on Machine Learning},
  year={2026}
}
```