@article{liberovifobenchmarkingthecapabilityandsa,
  title = {LIBERO-VIFO: Benchmarking the Capability and Safety of Visual Cue Following in Vision-Language-Action Models},
  author = {Zhengyan Qian and Rui Yan and Alex Jinpeng Wang and Jinhui Tang},
  year = {2026},
  eprint = {2608.17600},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2608.17600},
}