@article{selfcaptioningmultimodalinteractiontunin,
  title = {Self-Captioning Multimodal Interaction Tuning: Amplifying Exploitable Redundancies for Robust Vision Language Models},
  author = {Yuriel Ryan and Hei Man Ip and Adriel Kuek and Paul Pu Liang and Roy Ka-Wei Lee},
  year = {2026},
  eprint = {2605.08145},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2605.08145},
}