qwbu/univla-7b-224-sft-r2r

UniVLA: Learning to Act Anywhere with Task-centric Latent Actions

The model was presented in the paper UniVLA: Learning to Act Anywhere with Task-centric Latent Actions.

UniVLA-7b for R2R navigation tasks

Code can be found at https://github.com/OpenDriveLab/UniVLA.

🚀 Run the following script to start an evaluation on Room2Room:

python experiments/robot/r2r/run_r2r_eval.py \
--action_decoder_path   <action_decoder_path> \
--pretrained_checkpoint <pretrained_checkpoint> 

📝 Citation

If you find our models useful in your work, please cite our paper:

@article{bu2025univla,
  title={UniVLA: Learning to Act Anywhere with Task-centric Latent Actions}, 
  author={Qingwen Bu and Yanting Yang and Jisong Cai and Shenyuan Gao and Guanghui Ren and Maoqing Yao and Ping Luo and Hongyang Li},
  journal={arXiv preprint arXiv:2505.06111},
  year={2025}
}