StarVLA MetaWorld QwenPI-v3 LA Finetune
This repository contains the evaluated StarVLA/QwenPI-v3 checkpoint for MetaWorld MT50.
Checkpoint
- Model:
starvla_metaworld_qwenpiv3_la_finetune - Step:
60000 - Benchmark: MetaWorld MT50
- Reported overall success rate:
70.9% - Base VLM:
Qwen/Qwen2.5-VL-3B-Instruct
Files
checkpoints/steps_60000_pytorch_model.pt
config.yaml
config.full.yaml
dataset_statistics.json
dataset_statistics.json is required for action denormalization. Keep the directory structure unchanged if your inference server expects the checkpoint directory layout used by the released config.
Usage Notes
This checkpoint is intended to be loaded with the StarVLA/QwenPI-v3 codebase. The public configs use Qwen/Qwen2.5-VL-3B-Instruct as the base VLM path.
For inference, load:
checkpoints/steps_60000_pytorch_model.pt
For continued training or evaluation on your own machine, update:
datasets:
vla_data:
data_root_dir: ./metaworld_starvla
to your local MetaWorld data path.
Citation
If you use this checkpoint, please cite the corresponding StarVLA and LA4VLA work and this model repository.
LA4VLA:
@misc{lin2026la4vlalearningactseeing,
title={LA4VLA: Learning to Act without Seeing via Language-Action Pretraining},
author={Tao Lin and Yuxin Du and Yiran Mao and Zewei Ye and Yilei Zhong and Bing Cheng and Yiming Wang and Jiting Liu and Yang Tian and Junchi Yan and Feiran Wu and Zenan Meng and Hu Wei and Yuqian Fu and Gen Li and Bo Zhao},
year={2026},
eprint={2606.27295},
archivePrefix={arXiv},
primaryClass={cs.RO},
url={https://arxiv.org/abs/2606.27295},
}
StarVLA:
@article{community2026starvla,
title={StarVLA: A Lego-like Codebase for Vision-Language-Action Model Developing},
author={Community, StarVLA},
journal={arXiv preprint arXiv:2604.05014},
year={2026},
eprint={2604.05014},
archivePrefix={arXiv},
primaryClass={cs.RO}
}