跨国深谈

扩散 (diffusion)

12分钟阅读

跨国深谈← 返回←扩散 (diffusion)
扩散

扩散 (diffusion)

概念
本站收录 2 集 · 14 条金句 · 关联 10 个

集里怎么说它

① 提到它的金句

14 条

我认为 Martin Fowler 在某个时候在 2000 年代有这个术语叫语义扩散，这基本上意味着一个人提出了一个术语，每个人都开始用他们自己的定义来糟蹋它，然后你就会失去它的实际定义。
I think Martin Fowler at some point had this term called semantic diffusion back in the 2000s, which kind of means that someone comes up with a term, everybody starts butchering it with their own definitions and then you kind of lose the actual definition of it.
—— Kiriti Badam · [39:30]

指向原始笔记的链接

我不认为在根本上可以阻止信息或模型能力的扩散。
I don’t think it’s fundamentally possible to prevent the diffusion of information or model capabilities.
—— Neil Movva · [67:51]

指向原始笔记的链接

现代生成式 AI，包括概率模型、扩散模型和许多其他东西，它们的数学结果等同于描述现代非平衡统计力学或热力学的数学。
Modern generative AI, including probabilistic models, including diffusion models, and many other things, their mathematics turns out to be equivalent to the mathematics that describes modern non-equilibrium statistical mechanics or thermodynamics.
—— Max Welling · [35:06]

指向原始笔记的链接

扩散模型其实就是一个把结构取来并毁掉的过程，这通常是世界上发生的事，熵随之上升；然后我们尝试在时间上逆转它——从噪声出发创造结构，这就是我们的生成模型。
So diffusion models really are a process by which you take structure and you destroy it, which is typically what happens in the world. The entropy goes up. And then we try to reverse that backward in time, which is to start with noise and create structure, which is our generative models.
—— Max Welling · [41:02]

指向原始笔记的链接

任何技术的扩散都需要一代人。
Diffusion of any technology takes a generation.
—— Varun Shenoy · [02:29]

指向原始笔记的链接

我认为 AI 的扩散也许是未来 20 年唯一最重要的问题。
I would argue AI diffusion is perhaps the single most important problem for the next 20 years.
—— Varun Shenoy · [02:36]

指向原始笔记的链接

看看电力作为一项技术的扩散，从电力的诞生到重组工厂，我们花了四十年。
If you look at the diffusion of electricity as a technology, it took 40 years for us to get from the inception of electricity to reorganizing factories.
—— Anish Acharya · [09:29]

指向原始笔记的链接

AI 能力的广泛扩散有非常重要和好的一面，因为如果只有一个或少数几个实体，就会存在权力集中的风险。
And again, there’s something very important and good about the diffusion broadly of AI capabilities because there’s a risk of concentration of power if one or a few entities people.
—— Greg Brockman · [10:18]

指向原始笔记的链接

第一，硅谷必须为扩散所需要的时间比他们以为的要长得多做好准备——或者说「我们」，但我其实指的是他们，因为我知道这会花多长时间。
One, Silicon Valley has to prepare for diffusion taking a lot longer than they think, or then I’ll say we, but I really think they because I know how long it’ll take.
—— Aaron Levie · [53:39]

指向原始笔记的链接

因为它是 diffusion，因为你同时输出很多 token，我们能够比自回归模型快大约 10 倍地生成文本。
Because it’s diffusion, because you’re outputting many tokens at the same time, we were able to generate text like 10x faster compared to the autoregressive model.
—— Stefano Ermon · [05:36]

指向原始笔记的链接

在 Inception，我们押注 diffusion 模型，因为我们相信最终重要的是推理时扩展。
At inception, we’re betting on diffusion models because we believe that what matters eventually will be inference time scaling.
—— Stefano Ermon · [08:01]

指向原始笔记的链接

你没法在 VLLM 或 SGLang 上运行这些基于扩散的 LLM。我们必须构建自己的服务引擎，而且我们能处理真实生产工作负载的很多复杂性。
You cannot run these diffusion-based LLMs on VLLM or SGLang. We had to build our own serving engine, and we can handle a lot of the complexity of real production workloads.
—— Stefano Ermon · [13:01]

指向原始笔记的链接

从根本上说，每当你训练一个生成式模型时，你所做的，无论是自回归模型还是某种程度上甚至是扩散模型，都是你试图通过本质上构建一个压缩方案来识别数据中的结构。
And fundamentally, if you think about whenever you train a generative model, what you’re doing is, whether it’s an autoregressive model or to some extent even a diffusion model, is you are trying to identify structure in the data by essentially building a compression scheme.
—— Stefano Ermon · [22:34]

指向原始笔记的链接

所以至少在学术文献中有大量证据表明，扩散模型更容易控制，而且有不同的引导方式——那些是自回归模型根本做不到的。
And so there is a lot of evidence in the academic literature, at least, that diffusion models are easier to control and there are different ways of steering them. That are just not possible with autoregressive models.
—— Stefano Ermon · [26:53]

指向原始笔记的链接

② 出现在这些集

2 集

③ 关联

点进去有真内容 —— 本页主要出口

Sam Charrington · Stefano Ermon · Justin Johnson · inception 阶段 · World Labs · Mercury · 世界模型 · 自回归模型 · 高斯溅射 · 推理

反向链接