Physical Intelligence 提出多尺度具身记忆 MEM，让机器人记住 15 分钟事件
We’ve developed a memory system for our models that provides both short-term visual memory and long-term semantic memory.
AI 导读
Physical Intelligence 为自家模型开发了多尺度具身记忆系统 MEM，用不同模态表示不同时间尺度的记忆。短期记忆由高效视频编码器保留近期交互的细粒度细节，长期记忆则通过训练模型用文本总结事件，最长可记住 15 分钟。该系统让机器人能完成清理整个厨房、从头准备烤奶酪三明治等多阶段真实任务，并展现出从过往错误中即时调整行为的上下文适应迹象。
正文
当前显示原文，中文全文译文尚未就绪。
We’ve developed a memory system for our models that provides both short-term visual memory and long-term semantic memory.
Our approach allows us to train robots to perform long and complex tasks, like cleaning up a kitchen or preparing a grilled cheese sandwich from scratch 👇 https://t.co/RlcqmZEP6M