Attention Alignment Between Humans and Vision-Language Models

Isaac R. Christian, Udith Haputhanthrige, Hanna Hornfeld, Declan Campbell, Samuel A. Nastase, Taylor W. Webb, Michael S. A. GrazianoarXiv 2026 · DOI

BibTeX
@misc{christian2026attention,
  author = {Isaac R. Christian and Udith Haputhanthrige and Hanna Hornfeld and Declan Campbell and Samuel A. Nastase and Taylor W. Webb and Michael S. A. Graziano},
  title = {{Attention Alignment Between Humans and Vision-Language Models}},
  year = {2026},
  eprint = {2606.17410},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2606.17410},
}

Loading related content...

Figure