@article{pixelvlaadvancingpixellevelunderstanding,
  title = {PixelVLA: Advancing Pixel-level Understanding in Vision-Language-Action Model},
  author = {Wenqi Liang and Gan Sun and Yao He and Jiahua Dong and Suyan Dai and Ivan Laptev and Salman Khan and Yang Cong},
  year = {2025},
  eprint = {2511.01571},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2511.01571},
}