Sparse Autoencoders enable Robust and Interpretable Fine-tuning of CLIP models

@misc{morelli2026sparse,
  title = {Sparse Autoencoders enable Robust and Interpretable Fine-tuning of CLIP models},
  author = {Fabian Morelli and Arnas Uselis and Ankit Sonthalia and Seong Joon Oh},
  year = {2026},
  eprint = {2605.15961},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2605.15961},
}