@article{depthcachedepthguidedtrainingfreevisualt,
  title = {DepthCache: Depth-Guided Training-Free Visual Token Merging for Vision-Language-Action Model Inference},
  author = {Yuquan Li and Lianjie Ma and Han Ding and Lijun Zhu},
  year = {2026},
  eprint = {2603.10469},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2603.10469},
}