arXiv · 2025 · Preprint

Actions as Language: Fine-Tuning VLMs into VLAs Without Catastrophic Forgetting

Asher Hancock, Xindi Wu, Lihan Zha, Olga Russakovsky, Anirudha Majumdar

Rendered by arXiv from the LaTeX source. If anything looks wrong, switch to the PDF.HTML · PDF · Open in a new tab ↗ · Close

Date: 2025-09-26
Citations: 49
arXiv: 2509.22195 ↗

Cite

@misc{hancock2025actions,
  title = {Actions as Language: Fine-Tuning VLMs into VLAs Without Catastrophic Forgetting},
  author = {Asher Hancock and Xindi Wu and Lihan Zha and Olga Russakovsky and Anirudha Majumdar},
  year = {2025},
  eprint = {2509.22195},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2509.22195},
}