LingBot-VLA 2.0 (base)
LingBot-VLA 2.0 converted for LeRobot (policy.type=lingbot_vla_v2): a Qwen3-VL-4B backbone with a sparse-MoE Qwen2 action expert, trained with flow matching.
Pre-trained base checkpoint, the starting point for fine-tuning on a new robot.
The weights are the upstream robbyant/lingbot-vla-v2-6b weights, unchanged (fp32, every tensor checked against upstream), with a LeRobot config and processors.
Usage
lerobot-train \
--policy.path=lerobot/lingbot_vla_v2_base \
--dataset.repo_id=<your_dataset> \
--policy.state_slots=... --policy.action_slots=... \
--policy.repo_id=<your_repo_id>
See the docs for the slot mapping of your robot.
License
Apache-2.0, as the upstream release. Fine-tuning with the dual-query distillation (on by default) downloads frozen teachers under their own licenses, including DINO-Video weights under the DINOv3 License. Inference does not use them.
Citation
@article{lingbotvla2,
title={From Foundation to Application: Improving VLA Models in Practice},
author={Wei Wu and others},
journal={arXiv preprint arXiv:2607.06403},
year={2026}
}