EmBARDiment:用于提升 XR 生产力的具身 AI 智能体
EmBARDiment: an Embodied AI Agent for Productivity in XR
AI总结:
本文提出 EmBARDiment,通过注意力框架融合 XR 中的用户动作、视线与情境记忆,隐式推断上下文,减少显式提示依赖并提升生产力交互体验。
摘要:
运行由大语言模型(LLM)驱动的聊天机器人的 XR 设备,有望成为常驻在线的智能体,从而支持更好的生产力场景。当前基于屏幕的聊天机器人并未利用 XR 中可用的全套自然输入,包括向内传感器数据;相反,它们过度依赖显式语音或文本提示,有时还会附带作为查询一部分而被丢弃的多模态数据。我们提出一种利用注意力框架的解决方案,该框架在 XR 环境中从用户动作、视线和情境记忆中隐式获取上下文。我们的工作最大限度地减少了对工程化显式提示的需求,促进了扎根且直观的交互,从而为聊天机器人收集用户洞察。
英文摘要:
XR devices running chat-bots powered by Large Language Models (LLMs) have the to become always-on agents that enable much better productivity scenarios. Current screen based chat-bots do not take advantage of the the full-suite of natural inputs available in XR, including inward facing sensor data, instead they over-rely on explicit voice or text prompts, sometimes paired with multi-modal data dropped as part of the query. We propose a solution that leverages an attention framework that derives context implicitly from user actions, eye-gaze, and contextual memory within the XR environment. Our work minimizes the need for engineered explicit prompts, fostering grounded and intuitive interactions that glean user insights for the chat-bot.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。