@article{m3vqaabenchmarkformultimodalmultientitym,
  title = {M$^3$-VQA: A Benchmark for Multimodal, Multi-Entity, Multi-Hop Visual Question Answering},
  author = {Jiatong Ma and Longteng Guo and Yuchen Liu and Zijia Zhao and Dongze Hao and Xuanxu Lin and Jing Liu},
  year = {2026},
  eprint = {2604.25122},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2604.25122},
}