@inproceedings{jiang-etal-2025-memory,
    title = "Memory-{QA}: Answering Recall Questions Based on Multimodal Memories",
    author = "Jiang, Hongda  and
      Zhang, Xinyuan  and
      Garg, Siddhant  and
      Arora, Rishab  and
      Kuo, Shiun-Zu  and
      Xu, Jiayang  and
      Colak, Aaron  and
      Dong, Xin Luna",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-main.1234/",
    pages = "24255--24277",
    ISBN = "979-8-89176-332-6",
    abstract = "We introduce Memory-QA, a novel real-world task that involves answering recall questions about visual content from previously stored multimodal memories. This task poses unique challenges, including the creation of task-oriented memories, the effective utilization of temporal and location information within memories, and the ability to draw upon multiple memories to answer a recall question. To address these challenges, we propose a comprehensive pipeline, Pensieve, integrating memory-specific augmentation, time- and location-aware multi-signal retrieval, and multi-memory QA fine-tuning. We created a multimodal benchmark to illustrate various real challenges in this task, and show the superior performance of Pensieve over state-of-the-art solutions (up to +14{\%} on QA accuracy)."
}