扩散模型 (diffusion models)
集里怎么说它
- 《让药物研发变成写代码:Chai Discovery 的 AI 分子设计之路》(05:40起):本集把它描述为一种逐步去噪的生成式 AI 方法,在 2021-2022 年成熟,让大家能同时生成蛋白质的结构和序列,突破了生物学的设计瓶颈。
- 《用物理设计新材料:Max Welling 的 AI for Science 双向之路》(35:06起):本集说第一篇扩散模型论文标题里就写了非平衡热力学——前向过程是结构被摧毁(熵增),反向过程是从噪声里创造结构(生成),是热力学熵增和逆转的直接对应
① 提到它的金句
4 条
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。
指向原始笔记的链接
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]
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。
指向原始笔记的链接
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]
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。
指向原始笔记的链接
At inception, we’re betting on diffusion models because we believe that what matters eventually will be inference time scaling.
—— Stefano Ermon · [08:01]
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。
指向原始笔记的链接
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]
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
Josh · Sam Charrington · Matt · Max Welling · Chai Discovery · cusp.ai · OpenAI · 智能体 · 药物发现 · 等变性
