LightMem-Ego：你的日常生活AI記憶

摘要

個人AI助手在行動與穿戴式裝置上，透過視覺與音訊串流持續感知使用者的日常生活。然而，回答關於過往經歷的查詢需要能持續累積、組織並檢索長期經歷的輕量多模態記憶，這仍是一項挑戰。為解決此問題，我們提出LightMem-Ego，一個專為日常生活輔助設計的輕量串流多模態記憶系統。該系統持續擷取第一人稱視角的視覺與音訊串流，將其對齊至共同時間軸，並組織成包含當前記憶、短期記憶與長期記憶的階層式記憶結構。當使用者提出查詢時，LightMem-Ego會動態將檢索導向至適當的記憶層級，並根據多模態證據生成答案。此示範可部署於智慧型手機與AI眼鏡上，支援物品尋找、對話回憶、生活摘要、習慣發現與個人化輔助等功能。程式碼已於 https://github.com/zjunlp/LightMem-Ego 公開。

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：你的日常生活AI記憶

LightMem-Ego: Your AI Memory for Everyday Life

摘要

Support