@inproceedings{chung-etal-2025-models,
    title = "Are Any-to-Any Models More Consistent Across Modality Transfers Than Specialists?",
    author = "Chung, Jiwan  and
      Yoon, Janghan  and
      Park, Junhyeong  and
      Lee, Sangeyl  and
      Yang, Joowon  and
      Park, Sooyeon  and
      Yu, Youngjae",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingestion-acl-25/2025.acl-long.130/",
    pages = "2595--2606",
    ISBN = "979-8-89176-251-0",
    abstract = "Any-to-any generative models aim to enable seamless interpretation and generation across multiple modalities within a unified framework, yet their ability to preserve relationships across modalities remains uncertain. Do unified models truly achieve cross-modal coherence, or is this coherence merely perceived? To explore this, we introduce ACON, a dataset of 1,000 images (500 newly contributed) paired with captions, editing instructions, and Q{\&}A pairs to evaluate cross-modal transfers rigorously. Using three consistency criteria{---}cyclic consistency, forward equivariance, and conjugated equivariance{---}our experiments reveal that any-to-any models do not consistently demonstrate greater cross-modal consistency than specialized models in pointwise evaluations such as cyclic consistency. However, equivariance evaluations uncover weak but observable consistency through structured analyses of the intermediate latent space enabled by multiple editing operations. We release our code and data at https://github.com/JiwanChung/ACON."
}