---
license: apache-2.0
library_name: openpi
tags:
- robotics
- vla
- pi0.5
- libero
- libero-goal
- libero-para
- paraphrase-robustness
pipeline_tag: robotics
base_model:
- physical-intelligence/pi05
---

# Pi 0.5 — LIBERO-Goal (expert-only)

Pi 0.5 with the **action expert fine-tuned on LIBERO-Goal** while keeping
the VLM backbone (PaliGemma 2 LLM) frozen at the base Pi 0.5 weights.
Released to enable reproduction of the
[**LIBERO-Para**](https://github.com/cau-hai-lab/LIBERO-Para) benchmark
(paraphrase-robustness evaluation of VLA models).

This is the `Pi05_expert` model in the paper's 7-model comparison.

> **What "expert-only" means here.** Pi 0.5 is a two-stack VLA: a VLM
> (PaliGemma 2 LLM + image encoder) for language/vision grounding, plus a
> flow-matching **action expert** that produces low-level actions. In this
> checkpoint **only the action expert was fine-tuned** on LIBERO-Goal
> demonstrations; the LLM stays at the original Pi 0.5 base weights.
> This isolates *action-side adaptation* from any change to the
> language/vision representation, which is the variant we use in the paper
> when probing paraphrase robustness.

| | |
|---|---|
| Base | [Pi 0.5](https://www.physicalintelligence.company/blog/pi05) (Physical Intelligence) |
| Architecture | PaliGemma 2 VLM + flow-matching action expert |
| Fine-tuned modules | **action expert only** (VLM kept frozen at base Pi 0.5 weights) |
| Fine-tune data | LIBERO-Goal demonstrations |
| Batch size | 256 |
| Steps | **30 000** |
| Format | Orbax sharded (`params/` for inference, `train_state/` for resume) |
| Total size | ~14.6 GB (`params` 5.8 GB + `train_state` 8.8 GB) |
| Eval benchmark | [LIBERO-Para](https://github.com/cau-hai-lab/LIBERO-Para) (1 base eval + 4 092 paraphrases × 5 seeds) |

## Companion codebase

- **Benchmark / eval / metrics**: https://github.com/cau-hai-lab/LIBERO-Para
  Official code for *"LIBERO-Para: A Diagnostic Benchmark and Metrics for Paraphrase
  Robustness in VLA Models"* (arXiv 2603.28301). Contains:
  - 4 092 paraphrased LIBERO-Goal instructions across 43 cells (Object × Action types)
  - PRIDE metric implementation (S_K, S_T, PD)
  - Per-model eval scripts for the 7 VLAs reported in the paper
  - Cell-level SR analysis & cross-model trajectory analysis
- **VLA training code**: [Physical-Intelligence/openpi](https://github.com/Physical-Intelligence/openpi) (use its
  LIBERO config + this checkpoint).

## Directory layout

```
.
├── README.md
├── _CHECKPOINT_METADATA
├── params/             # 5.8 GB — model weights (download this for inference)
│   ├── manifest.ocdbt
│   ├── _METADATA
│   ├── _sharding
│   ├── array_metadatas/
│   ├── d/
│   └── ocdbt.process_0/
└── train_state/        # 8.8 GB — optimizer + EMA state (download only to resume training)
    └── ... (same Orbax layout)
```

## Quick start — inference

```bash
pip install huggingface_hub openpi  # openpi is required for inference
```

```python
from huggingface_hub import snapshot_download
from openpi.training import config as _config
from openpi.policies import policy_config

# 1. Download checkpoint (params + metadata only — ~5.8 GB)
ckpt_dir = snapshot_download(
    repo_id="HAI-Lab/pi05-libero_goal-expert_only",
    allow_patterns=["params/**", "_CHECKPOINT_METADATA"],
)

# 2. Build policy with the LIBERO-Goal config (defined in openpi)
config = _config.get_config("pi05_libero")          # or your own config
policy = policy_config.create_trained_policy(config, ckpt_dir)

# 3. Inference
# obs = {"image": ..., "state": ..., "prompt": "open the middle drawer"}
# action = policy.infer(obs)
```

## Quick start — LIBERO-Para paraphrase-robustness eval

```bash
git clone https://github.com/cau-hai-lab/LIBERO-Para
cd LIBERO-Para

# Follow the per-model eval guide (Pi 0.5 section):
#   eval_guides/pi05.md
# pointing it at this checkpoint:
#   /path/to/HAI-Lab/pi05-libero_goal-expert_only
```

The repo will run the **4 092 paraphrase × 5 seed × 10 task** sweep, compute
per-cell success rates, and report PRIDE / S_K / S_T scores reproducing
Table X of the paper for the `Pi05_expert` row.

## Reproducing the `Pi05_expert` paper numbers

| metric | value |
|---|---:|
| Overall SR (canonical LIBERO-Goal, mean across 5 seeds) | (filled in by eval scripts) |
| LIBERO-Para SR (4 092 paraphrases, mean across 5 seeds) | (see paper Table X) |
| PRIDE (α = 0.5) | (see paper Table X) |

Run [LIBERO-Para](https://github.com/cau-hai-lab/LIBERO-Para)'s
`scripts/run_eval_pi05_expert.sh` (or equivalent) to regenerate.

## Resuming training

```python
ckpt_dir = snapshot_download(
    repo_id="HAI-Lab/pi05-libero_goal-expert_only",
)  # full repo, includes train_state/
```

Then point your `openpi` training config's `resume_from` at `ckpt_dir`.

## Citation

If you use this checkpoint, please cite both the LIBERO-Para paper and the
original Pi 0.5 release:

```bibtex
@misc{kim2026liberoparadiagnosticbenchmarkmetrics,
      title={LIBERO-Para: A Diagnostic Benchmark and Metrics for Paraphrase Robustness in VLA Models},
      author={Chanyoung Kim and Minwoo Kim and Minseok Kang and Hyunwoo Kim and Dahuin Jung},
      year={2026},
      eprint={2603.28301},
      archivePrefix={arXiv},
      primaryClass={cs.LG},
      url={https://arxiv.org/abs/2603.28301},
}

@misc{pi05_2025,
  title  = {{\pi}-0.5: A Vision-Language-Action Model with Open-World Generalization},
  author = {{Physical Intelligence}},
  year   = {2025},
  url    = {https://www.physicalintelligence.company/blog/pi05},
}
```

## License

Apache 2.0 — same as the base Pi 0.5 release.
The LIBERO-Para benchmark and its evaluation code are MIT-licensed.
By using this checkpoint you also agree to Physical Intelligence's terms for
the Pi 0.5 base model.

## Acknowledgments

- [Physical Intelligence](https://www.physicalintelligence.company/) — Pi 0.5 base model
- [LIBERO](https://libero-project.github.io/) — original benchmark
- [openpi](https://github.com/Physical-Intelligence/openpi) — training & inference framework
- [LIBERO-Para](https://github.com/cau-hai-lab/LIBERO-Para) — paraphrase-robustness benchmark