@inproceedings{kahatapitiya-etal-2025-language,
    title = "Language Repository for Long Video Understanding",
    author = "Kahatapitiya, Kumara  and
      Ranasinghe, Kanchana  and
      Park, Jongwoo  and
      Ryoo, Michael S",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/mtsummit-25-ingestion/2025.findings-acl.294/",
    doi = "10.18653/v1/2025.findings-acl.294",
    pages = "5627--5646",
    ISBN = "979-8-89176-256-5",
    abstract = "Language has become a prominent modality in computer vision with the rise of LLMs. Despite supporting long context-lengths, their effectiveness in handling long-term information gradually declines with input length. This becomes critical, especially in applications such as long-form video understanding. In this paper, we introduce a Language Repository (LangRepo) for LLMs, that maintains concise and structured information as an interpretable (i.e., all-textual) representation. Our repository is updated iteratively based on multi-scale video chunks. We introduce write and read operations that focus on pruning redundancies in text, and extracting information at various temporal scales. The proposed framework is evaluated on zero-shot visual question-answering benchmarks, showing state-of-the-art performance at its scale. Our code is available at https://github.com/kkahatapitiya/LangRepo."
}