@article{metbenchmultimodalentitytrackingfor,
  title = {MET-Bench: Multimodal Entity Tracking for Evaluating the Limitations of Vision-Language and Reasoning Models},
  author = {Vanya Cohen and Raymond Mooney},
  year = {2025},
  eprint = {2502.10886},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2502.10886v1},
}