@article{visionlanguagemodelslaghumanperformanceo,
  title = {Vision-language models lag human performance on physical dynamics and intent reasoning},
  author = {Tianjun Gu and Jingyu Gong and Zhizhong Zhang and Yuan Xie and Lizhuang Ma and Xin Tan and Athanasios V},
  year = {2026},
  eprint = {2601.01547},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2601.01547},
}