@article{xtokenizeramultimodalactiontokenizerforv,
  title = {X-Tokenizer: A Multimodal Action Tokenizer for Vision-Language-Action Pretraining},
  author = {Miracle Kang and Lights Shi and Lucy Liang and Roy Gan and Dongxiu Liu and Pushi Zhang and Sylas Chen and Shawn Qin and Yinan Zheng and Jinliang Zheng and Hao Wang and Xianyuan Zhan and Hang Su},
  year = {2026},
  eprint = {2606.14752},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2606.14752},
}