GPLA

Code accompanying the paper Grounding Hierarchical Vision-Language-Action Models Through Explicit Language-Action Alignment.

@misc{wulff2026groundinghierarchicalvisionlanguageactionmodels,
      title={Grounding Hierarchical Vision-Language-Action Models Through Explicit Language-Action Alignment},
      author={Theodor Wulff and Federico Tavella and Rahul Singh Maharjan and Manith Adikari and Angelo Cangelosi},
      year={2026},
      eprint={2604.05614},
      archivePrefix={arXiv},
      primaryClass={cs.RO},
      url={https://arxiv.org/abs/2604.05614},
}