@article{moeller2024explainingvisionlanguagesimilaritiesdual,
  added-at = {2024-09-23T16:14:14.000+0200},
  archiveprefix = {arXiv},
  author = {Möller, Lucas and Tilli, Pascal and Vu, Ngoc Thang and Padó, Sebastian},
  biburl = {https://puma.ub.uni-stuttgart.de/bibtex/267bce8a756b3f4caadaf1ff78f092c74/sp},
  eprint = {2408.14153},
  interhash = {7f8c73539476e5a2e564e85387bb6151},
  intrahash = {67bce8a756b3f4caadaf1ff78f092c74},
  journal = {Transactions on Machine Learning Research},
  keywords = {myown preprint unpublished},
  primaryclass = {cs.CV},
  timestamp = {2025-07-29T13:00:41.000+0200},
  title = {Explaining Caption-Image Interactions in CLIP models with Second-Order Attributions},
  url = {https://openreview.net/forum?id=HUUL19U7HP},
  year = 2025
}