Curiosity · AI Model
OpenVLA
OpenVLA is an open-source 7B vision-language-action model from Stanford, Google DeepMind, Toyota Research, and collaborators. It fine-tunes a Prismatic VLM (DINOv2 + SigLIP + Llama 2 7B) on 970k robot trajectories from the Open X-Embodiment dataset and outputs discretised 7-DoF actions. Weights and training code are fully open under an Apache-2.0-style licence, making it the go-to baseline for academic robotics research on generalist policies.
Model specs
- Vendor
- Stanford / Google DeepMind / TRI (collaboration)
- Family
- OpenVLA
- Released
- 2024-06
- Context window
- 1 tokens
- Modalities
- text, vision, code
Strengths
- Fully open weights + training code under permissive licence
- Outperforms RT-2-X on common benchmarks despite being smaller
- Efficient LoRA adaptation to new embodiments
- Active research community and downstream forks
Limitations
- Action space is tokenised — not as smooth as flow-matching policies like π0
- Single-arm table-top focus — locomotion and bi-manual less covered
- Requires 24 GB+ GPU for full-precision inference
- Needs task-specific fine-tuning for most production use
Use cases
- Open baseline for generalist manipulation research
- LoRA fine-tuning to new robots with small demonstration sets
- Comparative evaluation of VLA design choices
- Teaching and benchmarking embodied-AI curricula
Benchmarks
| Benchmark | Score | As of |
|---|---|---|
| BridgeV2 / RT-2-X evaluation suite | ≈16 pp higher success than RT-2-X on average | 2024-06 |
| LoRA fine-tune to new embodiment | matches scratch RT-2 with ~1% of compute | 2024-06 |
Frequently asked questions
What is OpenVLA?
OpenVLA is a 7B-parameter open-source vision-language-action model trained on the Open X-Embodiment robot dataset, released by Stanford, Google DeepMind, Toyota Research, and collaborators.
Why use OpenVLA instead of RT-2?
RT-2 weights are closed. OpenVLA is fully open, reproducible, and on common benchmarks slightly outperforms RT-2-X while being easier to fine-tune with LoRA.
What licence is OpenVLA under?
Weights and code are released under an MIT-style licence that allows research and commercial use, subject to the underlying data terms.
Sources
- OpenVLA project site — accessed 2026-04-20
- OpenVLA paper (arXiv) — accessed 2026-04-20