@article{vlmtvisionlanguagemultimodaltransformer,
  title = {VLMT: Vision-Language Multimodal Transformer for Multimodal Multi-hop Question Answering},
  author = {Qi Zhi Lim and Chin Poo Lee and Kian Ming Lim and Kalaiarasi Sonai Muthu Anbananthen},
  year = {2025},
  eprint = {2504.08269},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2504.08269v1},
}