GROVE：基于流视频体验的时间分层记忆的生长与推理
GROVE: Growing and Reasoning over Temporally Stratified Memory from Streaming Video Experience
浏览论文内容
中文总结 AI 辅助
GROVE是一种无训练框架，通过从流视频生长的时间分层记忆，实现可穿戴助手的反应式问答与主动辅助，在MM-lifelong等基准测试中表现最优。
中文摘要 AI 辅助
可穿戴助手应既能回答关于视觉历史的问题，又能识别该历史对当前情境的有用性。现有视频记忆系统主要支持基于问题的回忆，而主动助手通常使用独立的记忆与控制机制。我们提出GROVE，这是一种无训练框架，通过从连续视频流因果生长的单一记忆支持上述两种行为。GROVE保留细粒度感知证据，并将其逐步整合为带时间戳的时刻、连贯片段和跨日重复模式。每个层级都配有适配其尺度的检索技能，用于定位观察结果、回放活动或遍历长期规律。反应式问答与主动助手共享该记忆及访问接口，区别仅在于检索是由用户查询还是当前情境触发。在包括极具挑战性的MM-lifelong和EgoServe在内的多个基准测试中，GROVE在对比方法中取得最优结果。受控消融实验表明，时间层级及其访问技能具有互补性，当证据跨多天时，模式带来的收益最大。代码将发布于该https URL。
英文摘要
A wearable assistant should both answer questions about its visual history and recognize when that history is useful to the present situation. Existing video-memory systems primarily support question-conditioned recall, whereas proactive assistants typically use separate memory and control mechanisms. We introduce GROVE, a training-free framework that supports both behaviors with one memory grown causally from a continuous video stream. GROVE retains fine-grained perceptual evidence and incrementally consolidates it into time-stamped moments, coherent episodes, and recurring cross-day patterns. Each stratum is paired with a scale-native retrieval skill for locating an observation, replaying an activity, or traversing long-range regularities. Reactive QA and proactive assistance share this memory and access interface, differing in whether retrieval is initiated by a user query or the current situation. Across multiple benchmarks including the challenging MM-lifelong and EgoServe, GROVE achieves the best results among the compared methods. Controlled ablations show that the temporal strata and their access skills are complementary, with patterns providing the largest benefit when evidence spans multiple days. Code will be available at https://github.com/SitongGong/GROVE.
