@article{visfactorbenchmarkingfundamentalvisual,
  title = {VisFactor: Benchmarking Fundamental Visual Cognition in Multimodal Large Language Models},
  author = {Jen-tse Huang and Dasen Dai and Jen-Yuan Huang and Youliang Yuan and Xiaoyuan Liu and Wenxuan Wang and Wenxiang Jiao and Pinjia He and Zhaopeng Tu},
  year = {2025},
  eprint = {2502.16435},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2502.16435v1},
}