@article{vegavisualencodergroundingalignmentforsp,
  title = {VEGA: Visual Encoder Grounding Alignment for Spatially-Aware Vision-Language-Action Models},
  author = {Hao Wang and Xiaobao Wei and Jingyang He and Chengyu Bai and Chun-Kai Fan and Jiajun Cao and Jintao Chen and Ying Li and Shanyu Rong and Ming Lu and Xiaozhu Ju and Jian Tang and Shanghang Zhang},
  year = {2026},
  eprint = {2605.10485},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2605.10485},
}