测试时扩展如何影响机器人
How does test-time scaling impact robots?
AI 导读
测试时扩展如何影响机器人？ 我们发现，更大的模型、更多的思考以及更多的上下文，对某些提示词有显著帮助，但对另一些则不然。 与 LLM 类似，我们也可以训练一个路由器，以实现更好的性能/延迟权衡！
查看原帖test-time compute [ttc] in robotics isn't free & isn't always worth it. smart allocation of ttc recovers frontier-level planning at a fraction of the cost! coauthor @milanganai w/ Yasmina @ajaysridhar0 Mozghan @katielulula Clark Barrett @jiajunwu_cs @chelseabfinn @drmapavone 🧵 https://t.co/USSHOuMm14
正文
当前显示原文，中文全文译文尚未就绪。
How does test-time scaling impact robots?
We find that larger models, more thinking, and more context help significantly for some prompts but not others.
Like LLMs, we can also train a router to for a better performance/latency tradeoff!