Self-Evolving Just-In-Time Memory for Proactive Embodied Safety
英文标题：Self-Evolving Just-In-Time Memory for Proactive Embodied Safety
arXiv:2607.16247v1 Announce Type: new Abstract: While Vision-Language Models (VLMs) have empowered embodied agents to execute complex household tasks, they struggle to proactively handle dynamically emerging hazards during closed-loop interactions. Existing safety approaches often rely on runtime g
打开原文相关 2.4 · 机会 1
2.1 KB
612 B
380 B
9.1 KB
32.7 KB
22.8 KB
24.2 KB
34.7 KB
中文
arXiv:2607.16247v1 Announce Type: new Abstract: While Vision-Language Models (VLMs) have empowered embodied agents to execute complex household tasks, they struggle to proactively handle dynamically emerging hazards during closed-loop interactions. Existing safety approaches often rely on runtime g
中文全文翻译正在补齐，可先查看下方英文原文。
English / 原文
BibTeX formatted citation
×