@article{vistaqabenchmarkingjointvisualquestionan,
  title = {VISTAQA: Benchmarking Joint Visual Question Answering and Pixel-Level Evidence},
  author = {Mozhgan Nasr Azadani and Yimu Wang and Yongpeng Zhu and Lihong Chen and Milan Ganai and Sean Sedwards and Marco Pavone and Krzysztof Czarnecki},
  year = {2026},
  eprint = {2605.20676},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2605.20676},
}