Open 7B Vision-Language-Action model pretrained on Open X-Embodiment (~970k demos). Canonical paper is arXiv:2406.09246 (2024); for 2025 finetuning SOTA see OpenVLA-OFT (arXiv:2502.19645).
Canonical open generalist manipulation VLA (~7B) on Open X-Embodiment — still the default open baseline in many 2026 comparisons.
OpenVLA is a fully open Vision-Language-Action model trained on Open X-Embodiment. It is a landmark release because weights, code, and data recipes are available enough for outside labs to finetune and study VLA behavior without a closed API.
The Paper button points to the canonical model paper (arXiv:2406.09246, June 2024, later revised on arXiv). That date is expected: it is the definition paper for the base 7B OpenVLA checkpoint—not a sign that the ecosystem stopped. The main 2025 follow-up from the same line is OpenVLA-OFT (arXiv:2502.19645, RSS 2025), an optimized fine-tuning recipe that greatly improves LIBERO success and real-robot throughput; use the separate OpenVLA-OFT resource for that paper and code.
Architecturally OpenVLA connects a VLM backbone to action prediction for manipulation across embodiments in OXE. Practically, 7B-class models need serious GPUs for finetuning; inference benefits from chunking/OFT-style recipes.
VLA researchers; labs finetuning language-conditioned manipulators; open-source reproducibility work.
See OpenVLA repo README
git clone https://github.com/openvla/openvla.git
Strong open VLA baseline; heavier than SmolVLA, more open than many proprietary stacks.
Physical Intelligence generalist VLA (~3B) with flow-matching actions; π0 weights are partially open — strong dexterous-manipulation reference in the π0 family.
NVIDIA foundation model series for humanoid and general robots combining sim and real data.
Content reviewed 2026-07-23
