LightMem-Ego：你日常生活的AI记忆

摘要

移动和可穿戴设备上的个人AI助手通过视觉和音频流持续感知用户的日常生活。然而，回答关于过往经历的查询需要一种能够持续积累、组织和检索长期经历的轻量级多模态记忆系统，这仍然具有挑战性。为应对这一挑战，我们提出了LightMem-Ego，一种用于日常生活辅助的轻量级流式多模态记忆系统。该系统持续捕捉第一人称的视觉和音频流，将其对齐到统一的时间线上，并组织成由当前记忆、短期记忆和长期记忆组成的层次化记忆。当收到用户查询时，LightMem-Ego会动态地将检索路由到相应的记忆层级，并基于多模态证据生成答案。该演示可部署于智能手机和AI眼镜，支持物体查找、对话回忆、生活总结、日常模式发现以及个性化辅助。代码已开源：https://github.com/zjunlp/LightMem-Ego。

English

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.

LightMem-Ego：你日常生活的AI记忆

LightMem-Ego: Your AI Memory for Everyday Life

摘要

Support