@article{vicaefficientmultimodalllmswithvisiononl,
  title = {ViCA: Efficient Multimodal LLMs with Vision-Only Cross-Attention},
  author = {Wenjie Liu and Hao Wu and Xin Qiu and Xudong Wang and Yingqi Fan and Yihan Zhang and Anhao Zhao and Yunpu Ma and Xiaoyu Shen},
  year = {2026},
  eprint = {2602.07574},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2602.07574},
}