新闻
Post-Train NVIDIA Cosmos 3 Edge for On-Device Robot Control
NVIDIA Developer · 发布于 · 阅读约3分钟
30秒读懂
- 发生了什么
- NVIDIA released Cosmos 3 Edge, a 4 billion parameter world model that runs on-device on Jetson Thor for real-time robot control without cloud offloading.
- 为何重要
- Roboticists deploying manipulation policies on edge hardware need models small enough for onboard memory while maintaining real-time control latency requirements.
- 注意
- The post-training requires 64 nodes of GB200 GPUs for 68 hours and achieves only 22.9 percent success on closed-loop tasks, indicating significant practical limitations remain.
收听本摘要
- post-train
- on-device
- edge
- nemotron
这条新闻背后的模式
每个模式都讲清楚技术如何运作、何时值得投入，以及在哪里会失效。
The Agent Architect
每周一个模式、一个权衡、一个生产事故案例。为构建智能体系统的人准备的每周简报。
每周一封邮件,一键退订。您的地址仅用于发送简报。