README.md

metadata

license: apache-2.0
pipeline_tag: robotics
library_name: transformers

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 CALVIN test suites

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

🚀 Run the following script to start an evaluation on CALVIN ABC-D:

# Mutli-GPU evaluation is supported
torchrun --standalone --nnodes 1 --nproc-per-node 8 experiments/robot/calvin/run_calvin_eval_ddp.py \
    --calvin_root /path/to/yout/calvin_root_path \
    --action_decoder_path /path/to/your/action_decoder.pt \
    --pretrained_checkpoint /path/to/your/calvin_finetuned_univla \
    --seed 7

📝 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}
}