@article{kidvisdomultimodallargelanguagemodelspos,
  title = {KidVis: Do Multimodal Large Language Models Possess the Visual Perceptual Capabilities of a 6-Year-Old?},
  author = {Xianfeng Wang and Kaiwei Zhang and Qi Jia and Zijian Chen and Guangtao Zhai and Xiongkuo Min},
  year = {2026},
  eprint = {2601.08292},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2601.08292},
}