@article{leveraginggazeandsetofmarkinvllmsforhuma,
  title = {Leveraging Gaze and Set-of-Mark in VLLMs for Human-Object Interaction Anticipation from Egocentric Videos},
  author = {Daniele Materia and Francesco Ragusa and Giovanni Maria Farinella},
  year = {2026},
  eprint = {2604.03667},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2604.03667},
}