@article{swiftvlmefficientvisionlanguagemodelinfe,
  title = {SwiftVLM: Efficient Vision-Language Model Inference via Cross-Layer Token Bypass},
  author = {Chen Qian and Xinran Yu and Danyang Li and Guoxuan Chi and Zheng Yang and Qiang Ma and Xin Miao},
  year = {2026},
  eprint = {2602.03134},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2602.03134},
}