@article{frompixelstotokensasystematicstudyoflate,
  title = {From Pixels to Tokens: A Systematic Study of Latent Action Supervision for Vision-Language-Action Models},
  author = {Yihan Lin and Haoyang Li and Yang Li and Haitao Shen and Yihan Zhao and Chao Shao and Jing Zhang},
  year = {2026},
  eprint = {2605.04678},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2605.04678},
}