Kirthana Gopalakrishnan
① 他说过的话
9 条
而做泛化就像是抬船，把所有船的水位都抬起来。
指向原始笔记的链接
And working on generalization is like lifting the boat, lifting the wave for all the boats.
—— Kirthana Gopalakrishnan · [15:23]
如果它只在你的机器人、你的特定配置上有效，那它真的是一个通用大脑吗？
指向原始笔记的链接
If it just works on your robot with your specific setup, is it really a generic brain?
—— Kirthana Gopalakrishnan · [20:41]
我认为我们会同时做出快的和慢的模型，然后把它们蒸馏成一个。
指向原始笔记的链接
I think we are going to simultaneously make the fast and the slow models and then distill them to one.
—— Kirthana Gopalakrishnan · [30:00]
虽然我们看到跨具身方面取得了巨大的飞跃，但我认为把一个新具身完全零样本地应用到很多任务上并达到很高的可靠性，这件事我认为还没有很强的先例。
指向原始笔记的链接
And while we see a large leap being made in cross-embodiment, I think that taking a new embodiment and completely zero-shotting it to a lot of tasks with very high reliability is still something that is, I don’t think there is a very strong precedent for that.
—— Kirthana Gopalakrishnan · [51:22]
如果你有 10 个任务按顺序执行，ER 模型有某个 x 成功率，VLA 模型有 y 成功率，那么如果你有一个按顺序执行的任务，你基本上就是在复合误差。
指向原始笔记的链接
if you have 10 tasks in sequence and now you have the ER model which has a certain x success rate and the VLA model which has a y success rate now the if you have a sequencing task you are basically compounding the error.
—— Kirthana Gopalakrishnan · [52:39]
人们不会指望它聪明，但一个人形机器人在那里乱摸一通、制造很多失败，就会被严厉得多地评判
指向原始笔记的链接
People don’t expect it to be smart, but a humanoid just grappling around and creating a lot of failures would be judged much harshly because
—— Kirthana Gopalakrishnan · [66:54]
而这也许是机器人领域工作最令人兴奋的部分之一，就是这个领域还很早期，配方还没有稳定下来。
指向原始笔记的链接
And this is maybe one of the most exciting parts of working in robotics is that it is still very early that the recipes haven’t stabilized.
—— Kirthana Gopalakrishnan · [74:14]
所以我认为在这件事上采取非常教条的立场是不明智的，因为随着新证据的出现和更好硬件的出现，这一切都会改变。
指向原始笔记的链接
So I don’t think it’s wise to take a very principled view about this because all of this will change as new evidence emerges and better hardware emerges.
—— Kirthana Gopalakrishnan · [78:31]
那些机器人没有一个是由机器学习驱动、连接到大模型的机器人，而现在情况已经非常不同了。
指向原始笔记的链接
None of those robots were machine-learned robots, which was connected to the large models, and now things are very different.
—— Kirthana Gopalakrishnan · [56:23]
② 出现在这些集
1 集
③ 他谈到的
点进去有真内容 —— 本页主要出口
Google DeepMind · Gemini Robotics · 人形机器人 · VLA · 泛化 · 跨载体 · 模拟 · 遥操作 · 世界建模 · ICL