Vinci2: Providing Proactive Assistance in Continuous Egocentric Videos

  • 类型：arxiv
  • 标识：2607.11523
  • 链接：https://arxiv.org/abs/2607.11523
  • 主分类：agent
  • 形态：method
  • 被引：2
  • 被引来源：Semantic Scholar
  • S2被引：2
  • OpenAlex被引：0
  • 影响力被引：0
  • TLDR：Vinci2 is presented, a proactive egocentric assistance system that advances the on-device assistant Vinci from reactive response toward proactivity and EgoMemo, a training-free, memory-augmented agent that maintains three complementary memory representations: multi-scale temporal summaries, a semantic knowledge graph, and visual embedding archives.
  • OpenAlex ID：W7168275645
  • OpenAlex DOI：10.48550/arxiv.2607.11523
  • DOI：10.48550/arxiv.2607.11523
  • DOI来源：OpenAlex
  • 开放获取：green
  • 开放获取链接：https://doi.org/10.48550/arxiv.2607.11523
  • OpenAlex更新：2026-07-19
  • 待LLM分类：否
  • 标题中文：Vinci2: Providing Proactive Assistance in Continuous Egocentric Videos
  • TLDR中文：论文提出 Vinci2，一个主动式的第一人称视频协助系统，将端侧助手 Vinci 由被动响应推进到主动协助；以及免训练、记忆增强的 Agent EgoMemo，维护三种互补的记忆表征：多尺度时间摘要、语义知识图谱与视觉嵌入档案。
  • 来源文件：
  • /inbox/tom/_candidates/2026-07-16-agent-rag-longcontext-candidates.json
  • [S2 enrich]
  • [OpenAlex backfill]