你的AI眼镜终于能记住昨天你把钥匙放哪了
你戴的AI眼镜或手机一直在看、在听，但问它“我昨天把钥匙放哪了”它答不上来——因为它没有长期记忆。这篇让设备把看到听到的按时间线存成“当前/短期/长期”三层记忆，你问什么它自动去对应层找，还能结合画面和声音回答。演示已跑在手机和AI眼镜上，能帮你找东西、回忆对话、总结一天。它不是你明天就能用的产品，但方向很明确：AI助手终于开始记得你。
📄 原文摘要(英文)
Personal AI assistants on mobile and wearable devices continuously perceive users' daily lives through visual and audio streams. However, answering queries about past experiences requires lightweight multimodal memory that can continuously accumulate, organize, and retrieve long-term experiences, which remains challenging. To address this challenge, we present LightMem-Ego, a lightweight streaming multimodal memory system for everyday-life assistance. The system continuously captures egocentric visual and audio streams, aligns them on a shared timeline, and organizes them into a hierarchical memory consisting of current, short-term, and long-term memory. Given a user query, LightMem-Ego dynamically routes retrieval to the appropriate memory level and generates answers grounded in multimodal evidence. The demonstration can be deployed on smartphones and AI glasses, supporting object finding, conversation recall, life summarization, routine discovery, and personalized assistance. Code is available at https://github.com/zjunlp/LightMem-Ego.