概念 · Module 4: Flow Matching

Continuous Normalizing Flow

— 用一条 ODE 把高斯流到数据;用 trace 替代行列式。

直觉:风把水从太平洋吹到大西洋

很多人第一次见 CNF 会以为它是「Normalizing Flow 的连续版」——意思好像是网络得设计成可逆的,再让步数趋近无穷。这是反过来的理解。CNF 的真正贡献并不是把 NF 的离散步数加密,而是用 ODE 一替代之后,网络可逆性这条枷锁直接消失,并且 Jacobian 行列式被替换成更便宜的 trace。换句话说,CNF 不是「让 NF 更细」,CNF 是「用微积分把 NF 当年绕不过去的两个工程难点同时拆掉」。这两个难点分别是:网络可逆性、Jacobian 可计算性。

在进入正式定义之前,先把家族关系摆清楚。Normalizing Flow(NF)是离散变换链 $x \to f_1 \to f_2 \to \cdots \to f_K \to z$,要求每个 $f_k$ 可逆、且 $\log|\det J_{f_k}|$ 能在 $O(d)$ 时间内算出。RealNVP、Glow、NICE 都属于 NF,它们都在「让网络好算 Jacobian」上做妥协。CNF 则直接把链条变成连续时间的 ODE,整条链条由一个共享的速度场 $v_\theta$ 决定,可逆性来自 ODE 解的存在唯一性定理,Jacobian 计算从行列式降到 trace。

「2018 年有一篇相当 seminal 的论文,叫 continuous normalizing flows 或者 Neural ODE。Ricky(陈天琦)当时是我的 Meta intern mentor,超级传奇。他提出 CNF:把一个初始分布——比如高斯——的样本,通过积分一条 ODE,变换成目标分布,比如图像分布。」
—— CMU 10799 L5(07:10–08:06)

CMU 的讲师给了一个非常直观的物理比喻:风把水从太平洋(西海岸)吹到大西洋(东海岸)。每一个时刻、每一个位置,风都有一个速度方向 $v_\theta(z, t)$;水分子(也就是你的样本 $z$)就跟着风一路飘到东岸。「流」这个词的意思就是「沿着速度场往前积分」。这里的水不是单个水分子,而是一整摊水的分布——风改变的不只是某一颗水珠的位置,而是整个分布的形状。

「想象风把太平洋的一摊水流向东海岸。为什么这是 normalizing flow?因为流线永远不会相交——如果你顺着风走,方向是唯一的,所以这是一个确定性的、可逆的变换。」
—— CMU 10799 L5(08:55–09:50)

"流线永远不会相交" 这句话是整个 CNF 直觉的灵魂。它意味着每个噪声点都对应唯一一个数据点,反过来每个数据点也对应唯一一个噪声点。这就是为什么 CNF 又叫 normalizing flow ——这个变换是双射,密度可以归一化、可以反过来追溯。一旦你接受了「沿着风走轨迹不会交叉」这件事,CNF 的所有数学就只是把它用微分方程的语言重新写一遍。换个说法:CNF 没有发明新的物理现象,它只是把"流体里的概率守恒"这件高中物理课上就出现过的事,用神经网络参数化、用 ODE 求解器跑起来。

Vizuara 的 Dr. Raj 把整个 flow 家族花了三到四节课讲,他在开场就提醒:

「flow models 有意思的地方是同一个主题可以用一节课讲完,也可以用四节课讲完。如果你走难的那条路——四节课——你最后会发现终点其实非常简单。一节课的路也能到终点,只是你不知道为什么。」
—— Vizuara Lecture 9(00:00–00:54)

这两位讲师的取向不同:CMU 直接从 flow matching 的"超简单形式"切入,先讲怎么"线性插值噪声和数据"再回头补 CNF 的数学;Vizuara 走慢路,先把 NF 的可逆性、Jacobian、change-of-variables 一层层铺开,最后才接到 CNF。两条路最后会汇到同一个出口:一条 ODE、一个速度场、一个 trace 公式。

🟡 教材外补充:在这一页里,我们沿 CMU 的"反向回溯"线路——先看 ODE 长什么样,再补为什么它配叫 normalizing flow。这是因为大多数读者来到这一页的时候,是从 diffusion 或 flow matching 反过来追根溯源的,而不是从经典 NF 演化过来的。在机器学习训练里,CNF 对应的位置就是:image / video / 3D 生成模型的积分式骨架——SD3、SORA、Movie Gen、Stable Audio 这些跑的都是 CNF 架构,只是用 flow matching 而不是 MLE 来训。

数学:ODE 三件套

① 前向 ODE。给一个时间相关的向量场 $v_\theta(z, t): \mathbb{R}^d \times [0,1] \to \mathbb{R}^d$,CNF 定义

$$\frac{dz(t)}{dt} = v_\theta(z(t), t), \quad z(0) \sim \mathcal{N}(0, I).$$

采样时把这条 ODE 从 $t=0$ 积到 $t=1$,得到 $z(1)$ 当作生成样本 $x$。数值积分一般用 Runge–Kutta 4 阶或者更高阶的自适应步长求解器(dopri5、dopri8),步数典型取 $20$–$100$ 之间。生成一张图的成本就是这么多次 forward pass。

Why:你只规定瞬时方向,不规定路径形状;网络只输出"在 $(z, t)$ 这个时空点上你该往哪走"。任何 MLP / U-Net / Transformer 都能当 $v_\theta$,无需任何结构约束——这就是 CNF 相对 NF 的头号红利。RealNVP 的 coupling layer、Glow 的 1x1 卷积都是为了让 Jacobian 容易算才设计的,到了 CNF 这些都不再必要。

② 瞬时变量替换公式(instantaneous change of variables)。普通 NF 算密度要 $\log\!\left|\det J\right|$,$d \times d$ 行列式是 $O(d^3)$;维度一大就死。Chen et al. 2018 证明在 ODE 极限下:

$$\frac{d \log p_t(z(t))}{dt} = -\,\mathrm{tr}\!\left(\frac{\partial v_\theta(z(t), t)}{\partial z}\right).$$

把 $\log\!\left|\det J\right|$ 这种"全局体积比"换成了 trace——速度场在每个点的瞬时散度。直观上:散度大于 0 表示这一点附近的"水"在膨胀,密度下降;散度小于 0 表示在收缩,密度上升。把这些瞬时变化沿时间积起来,就得到了任意时刻 $t$ 上的 $\log p_t$。

Why:trace 是 Jacobian 的对角元之和,对 $d=10^6$ 来说显式求所有对角元仍然要算 $d$ 次反传,依然不可行——但 Hutchinson 随机迹估计 $\mathrm{tr}(A) = \mathbb{E}_{\epsilon}[\epsilon^\top A \epsilon]$ 只需要采一个随机向量 $\epsilon$,做一次 Jacobian–向量积(VJP),就得到一个无偏估计。一次反传 $O(d)$ 就够,跟维度线性挂钩。这是 CNF 在高维上能跑起来的关键工程,也是 NF 时代不可能做到的——因为离散 NF 里你必须算精确 Jacobian 行列式,不能用随机估计。

③ 训练目标(经典 MLE)。沿 $t: 1 \to 0$ 反向积分 ODE,同时累计 $\log p$:

$$\log p_1(x) = \log p_0(z(0)) - \int_0^1 \mathrm{tr}\!\left(\nabla v_\theta\right) dt.$$

$p_0$ 是高斯,logpdf 闭式;$p_1(x)$ 是模型在数据点上的对数似然。最大化它,就是 CNF 的经典最大似然训练。注意这里的反向积分:拿到一个数据点 $x$,把它当作 $z(1)$,沿 ODE 反着积到 $t=0$,沿途累计 trace 项,最后用 $z(0)$ 的高斯对数密度算总账。整个过程是端到端可微的,但需要把整条 ODE 轨迹反向再跑一遍。反向传播则用 adjoint sensitivity method 把内存开销从 $O(\text{steps})$ 压到 $O(1)$(代价是再积一次 ODE)。

Why 用 adjoint:朴素地存下所有中间激活再反传,ODE solver 跑 100 步就要 100 倍内存,图像 batch 一上来就 OOM。Neural ODE 的 adjoint 把反传也写成一条 ODE:定义伴随状态 $a(t) = \partial L / \partial z(t)$,它本身满足 $da/dt = -a^\top \nabla_z v_\theta$,可以从 $t=1$ 反着积到 $t=0$。这样训练时只存终点状态,所有中间状态需要的时候再积一次拿到。这是 2018 论文的核心卖点之一,也是把 ODE 网络写进现代深度学习库的工程基础。

为什么叫 "normalizing flow"

"Normalizing" 指归一化变量替换——经过 $f$ 之后概率密度仍然是概率密度(积分为 1)。"Flow" 指沿速度场流动——确定性、轨迹不相交。两条性质合在一起就是:

「这个变换之所以叫 normalizing flow,是因为流线永远不会相交。流如果是确定性的,它就是可逆的——你可以反着积分回去。所以从任何一个数据点,你都能反推到它对应的那个噪声。」
—— CMU 10799 L5(09:30–10:18)

这一点在 diffusion / flow 整个家族里特别关键:可逆意味着likelihood 可算、latent 可控、image inversion 可做。SDS、DDIM inversion、image editing 都靠这条性质——你需要把一张真实图编辑回到 latent,做点操作,再 decode 回来。SDE 路线下需要近似算法才能勉强 invert,而 CNF/ODE 路线下 invert 就是把求解器反着跑一遍,干净利落。

训练慢、采样慢:CNF 一度被搁置的原因

2018 到 2021 这几年,CNF 的论文不多,主要原因就是慢。最大似然训练每一步要:(1) 反向积分 ODE;(2) 沿途算 Hutchinson trace;(3) 通过 adjoint 反传到参数。一个 epoch 跑下来几小时起步,比 GAN、VAE 慢一个量级以上。采样也慢——20 到 100 步 ODE 积分,比 VAE/GAN 的一次 forward 慢不少。这两个慢加起来让 CNF 在生成质量上虽然有理论优势,但实际表现长期被 GAN 压制。

真正让 CNF 翻身的是 2022 年 Lipman 等人的 Flow Matching:用 MSE 直接回归 velocity,跳过似然,跳过 trace,跳过 adjoint,训练快到和普通监督学习一样。再加上 SD3、SORA 这些大模型把 CNF + FM 推到 SOTA,CNF 这才正式接管 image / video / 3D 生成的主战场。

CMU 讲师的"反向重建"线路

CMU L5 整堂课的脉络其实是先给答案再追溯。讲师先抛出 flow matching 的极简形式——"取一个数据 $x_1$、取一个噪声 $x_0$、线性插值得到 $x_t = (1-t) x_0 + t x_1$、目标 velocity 是 $x_1 - x_0$、网络回归这个 velocity"——然后问:"为什么这么简单的东西居然就是合法的生成模型?为什么我们之前要绕一大圈走 SDE、score matching?"

「这看起来太简单了——没有数学,没有 SDE,什么都没有。为什么我们之前要做那么多 diffusion 的数学?为什么这居然是合法的?为什么这两种方法是等价的?我们凭什么可以这么做?答案要从历史讲起,2018 年才能讲明白。」
—— CMU 10799 L5(06:26–07:10)

接着讲师把整条历史线拉出来:2018 Neural ODE 提出 CNF 骨架;2019–2021 MLE 训 CNF 慢得没人用;2020 Song 提出 PF-ODE,把 diffusion 和 CNF 连起来;2022 Lipman 提出 flow matching,给了 CNF 一个不依赖似然的训练 shortcut。Flow matching 之所以"看起来太简单",是因为它站在 CNF 框架上——CNF 把可逆性和密度计算的复杂度都吸收掉了,FM 只需要管 velocity 的回归,自然就显得轻盈。

这个故事讲完之后,再回头看 flow matching 的 5 行训练代码,你就知道每一行背后都有 CNF 的数学撑着。这是为什么这一页要把 CNF 单独抽出来讲清楚:它是整个 flow 家族的母架构,所有后续的训练方法都是它的某种 shortcut。理解了 CNF,diffusion 的 SDE、PF-ODE、score matching、flow matching、rectified flow、consistency models 才能在一张图里看清楚相互的位置。

主要图示:向量场把高斯流到数据

$t=0$ 高斯 $v_\theta(z, t)$ 速度场 $t=1$ 数据双峰 $z(0)$ $z(1) = x$ 沿 ODE 积分 $\int_0^1 v_\theta \, dt$

左侧的蓝色高斯样本,被中间的速度场(橙色箭头)"吹"到右侧的双峰数据分布上。注意:箭头是 $v_\theta$ 在某些代表点的值,不是粒子轨迹——真实粒子轨迹是从这些箭头积分出来的曲线。一个粒子在某个位置看到的箭头,决定了它下一瞬该往哪走;下一瞬走到新位置后,又看到新箭头,继续走。把这些瞬时方向连成一条线,就是这个粒子的轨迹。

另一个值得说清楚的事:速度场 $v_\theta$ 是同一个网络,时间 $t$ 作为输入。你不是训 100 个不同的网络管 100 个时刻,而是训一个吃 $(z, t)$ 输出方向的网络。这一点和 NF 不同——NF 是堆叠 $K$ 个不同的可逆层,每层有独立参数。CNF 是 amortized:用时间编码(sinusoidal 或 learnable)把 $t$ 喂进网络,让一个网络管所有时刻。这是参数效率的来源,也是 flow matching 训练 shortcut 能成立的前提。

下面有 4 个按钮,依次切换"先验 → 速度场 → 流动中 → 数据"。不变量:整体质量守恒——所有蓝点的"总质量"等于所有橙点的"总质量",因为 ODE 是一一对应的双射,不创造也不销毁概率。

$t=0$:从标准高斯 $\mathcal{N}(0, I)$ 抽蓝点。

手算:1-D CNF 在一个时刻的密度更新

设 $d=1$,$v_\theta(z, t) = -0.5 z$(朝原点收缩的一个简单线性速度场)。已知 $z(0) = 2$,$\log p_0(z(0)) = -2.92$(标准高斯在 $z=2$ 处的对数密度,等于 $-\frac{1}{2}\log(2\pi) - 2 \approx -2.92$)。用 $\Delta t = 0.1$ 做一步显式 Euler:

$$z(0.1) = z(0) + v_\theta(z, 0)\,\Delta t = 2 + (-0.5)(2)(0.1) = 2 - 0.1 = 1.9.$$

瞬时散度 $\partial v_\theta / \partial z = -0.5$(这里 $v$ 是 $z$ 的一次函数,导数显然是 $-0.5$),所以瞬时变量替换给出:

$$\log p_{0.1}(z(0.1)) = \log p_0(z(0)) - \mathrm{tr}(\nabla v_\theta)\,\Delta t = -2.92 - (-0.5)(0.1) = -2.92 + 0.05 = -2.87.$$

密度上升了 0.05——符合直觉,因为收缩场把质量挤向中心,等价点的密度变大。如果速度场是发散的(比如 $v_\theta = +0.5 z$),同样的 Euler 一步会得到 $\log p$ 下降 0.05。这就是 trace 替代行列式后整套机器的样子:你只需要会算速度场对 $z$ 的导数(自动微分一行),不需要算任何 $d \times d$ 行列式。

三大常见误区

  1. "CNF 就是把 RealNVP 步数趋近无穷的极限。" 反例:RealNVP 必须用 coupling layer,强行把网络拆成两半交替更新——一半保持不变,另一半被对方调制——这样 Jacobian 就是分块三角,行列式只是对角元乘积。这是一个强结构约束。CNF 的 $v_\theta$ 可以是任意 MLP、U-Net、DiT、Transformer,没有可逆性约束——可逆性是 ODE 解的存在唯一性定理自动赋予的,不是网络结构赋予的。RealNVP 与 CNF 在表达力上不是连续过渡,而是两种不同范式。
  2. "CNF $=$ Diffusion。" 反例:Diffusion 是 SDE($dx = f\,dt + g\,dW$,含布朗运动 $dW$),轨迹是随机的,同一个起点跑两次终点不同;CNF 是 ODE(无随机项),完全确定,同一个起点跑无数次结果都一样。两者的桥梁是 PF-ODE——Yang Song 2020 证明每个扩散 SDE 都有一条等价的 probability flow ODE,这条 PF-ODE 与原 SDE 在任意时刻 $t$ 的边缘分布相同,PF-ODE 就是 CNF 的一种特例。换句话说:diffusion = 一个带 score-matching 训练 shortcut 的 CNF,速度场 $v_\theta$ 由学到的 score $\nabla \log p_t$ 间接构造。
  3. "CNF 必须 MLE 训练。" 反例:MLE 训练慢得让 CNF 一度被搁置整整四年(每步反向积分 + Hutchinson trace + adjoint,单 epoch 几小时起步;图像数据集上很难和 GAN 竞争)。Flow Matching(Lipman 2022)用 MSE 直接回归 velocity 取代 likelihood——给定一条预设的概率路径(高斯到数据),目标 velocity 有闭式解,训练就是普通监督学习。SD3、SORA、Flux 等大模型跑的都是 CNF 架构,但都用 FM 训。FM 是 CNF 的训练 shortcut,不是新模型,不是替代品。

相关概念

桥接 diffusion ↔ flow matching:CNF 是 diffusion 与 flow matching 共同的积分式骨架。从 diffusion 出发,把 SDE 的随机项扣掉得到 PF-ODE,这条 ODE 在结构上就是 CNF;从 flow matching 出发,预设一条概率路径,直接学 $v_\theta$,得到的也是 CNF。两条不同的路径同一个出口,差别只在怎么训这个 $v_\theta$。这也是为什么近年的论文越来越倾向于把 diffusion 和 flow matching 统一在 CNF 框架下讨论——它们不是两种东西,而是同一种东西的两种训练方法。
  • Flow Matching — CNF 的现代训练 shortcut,用 MSE 直接回归 velocity,跳过似然计算。
  • Velocity Field — CNF 的核心可学习对象 $v_\theta(z, t)$,决定了流的形状和速度。

来源

  1. cmu-10799-diffusion-flow · L5 · "2018 seminal paper / Ricky / Neural ODE" · (07:10)
  2. cmu-10799-diffusion-flow · L5 · "wind transports water, streams never cross" · (08:06)
  3. cmu-10799-diffusion-flow · L5 · "invertible because flow is deterministic" · (08:55)
  4. diffusion-principles-vizuara · L9 · "flow models 两条教学路径" · (00:03)
查看 117 条课程原文出处
CourseLectureTimeExcerpt
cmu-10799-diffusion-flow L5: CMU 10799 S26: Lecture 5 - Flow Matching - Diffusion & Flow Matching 00: 02 So last time we learned about how So last time we learned about how diffusion turn noise into data by diffusion turn noise into data by diffusion turn noise into data by gradually adding noise and gra…
cmu-10799-diffusion-flow L5: CMU 10799 S26: Lecture 5 - Flow Matching - Diffusion & Flow Matching 00: 52 by an SDE with this score function and then we can just do score matching to then we can just do score matching to then we can just do score matching to learn uh how to solve the uh the learn uh how t…
cmu-10799-diffusion-flow L5: CMU 10799 S26: Lecture 5 - Flow Matching - Diffusion & Flow Matching 01: 41 That's exactly correct. Okay. Why don't we just do linear interpolation of the we just do linear interpolation of the we just do linear interpolation of the two things, right? Um so exact how two thin…
cmu-10799-diffusion-flow L5: CMU 10799 S26: Lecture 5 - Flow Matching - Diffusion & Flow Matching 02: 26 this trajectory in this way. Um yeah so remember the same noise same data. remember the same noise same data. remember the same noise same data. Then learning the transformation along Then learning th…
cmu-10799-diffusion-flow L5: CMU 10799 S26: Lecture 5 - Flow Matching - Diffusion & Flow Matching 03: 28 progress. So like 0.25 time um times uh progress. So like 0.25 time um times uh data minus noise, right? Uh so basically data minus noise, right? Uh so basically data minus noise, right? Uh so basical…
cmu-10799-diffusion-flow L5: CMU 10799 S26: Lecture 5 - Flow Matching - Diffusion & Flow Matching 04: 20 this is literally what we need to learn, this is literally what we need to learn, right? This is like literally the only right? This is like literally the only right? This is like literally the only t…
cmu-10799-diffusion-flow L5: CMU 10799 S26: Lecture 5 - Flow Matching - Diffusion & Flow Matching 05: 17 Right? How do you progress through the chain? You just compute the displacement chain? You just compute the displacement chain? You just compute the displacement for x and then directly apply the for …
cmu-10799-diffusion-flow L5: CMU 10799 S26: Lecture 5 - Flow Matching - Diffusion & Flow Matching 06: 26 full matching. Class is over. Hey, no, not really. Okay, fine. Uh but no, not really. Okay, fine. Uh but no, not really. Okay, fine. Uh but basically the the question that we're basically the the ques…
cmu-10799-diffusion-flow L5: CMU 10799 S26: Lecture 5 - Flow Matching - Diffusion & Flow Matching 07: 10 people start to de develop this thing. Okay. So basically back in 2018 there Okay. So basically back in 2018 there Okay. So basically back in 2018 there this like pretty seminal paper um uh this like …
cmu-10799-diffusion-flow L5: CMU 10799 S26: Lecture 5 - Flow Matching - Diffusion & Flow Matching 08: 05 can just solve this OD by integrating can just solve this OD by integrating through uh the velocity and then you through uh the velocity and then you through uh the velocity and then you you'll be abl…
cmu-10799-diffusion-flow L5: CMU 10799 S26: Lecture 5 - Flow Matching - Diffusion & Flow Matching 08: 55 Anyone else I haven't talked to today? Nobody remember what is normalizing Nobody remember what is normalizing Nobody remember what is normalizing flow? >> You can reconstruct the process. >> You can …
cmu-10799-diffusion-flow L5: CMU 10799 S26: Lecture 5 - Flow Matching - Diffusion & Flow Matching 09: 50 invertible transformation because invertible transformation because everything is deterministic. everything is deterministic. everything is deterministic. Okay, any question? Okay, any question? Okay,…
cmu-10799-diffusion-flow L5: CMU 10799 S26: Lecture 5 - Flow Matching - Diffusion & Flow Matching 11: 01 no new mass uh is is going to get added and no mass is going to disappear and no mass is going to disappear and no mass is going to disappear getting dropped. So like translate it getting dropped. So …
cmu-10799-diffusion-flow L5: CMU 10799 S26: Lecture 5 - Flow Matching - Diffusion & Flow Matching 11: 50 probability flux. So imagine a flux is like the amount of flow the amount of like the amount of flow the amount of like the amount of flow the amount of water uh per unit per time that's going water u…
cmu-10799-diffusion-flow L5: CMU 10799 S26: Lecture 5 - Flow Matching - Diffusion & Flow Matching 12: 55 in a container. It's in like a contained in a container. It's in like a contained tank. So, the probability mass never tank. So, the probability mass never tank. So, the probability mass never change.…
cmu-10799-diffusion-flow L5: CMU 10799 S26: Lecture 5 - Flow Matching - Diffusion & Flow Matching 14: 00 in math in this way. So this is like in math in this way. So this is like basically like how much probability gets basically like how much probability gets basically like how much probability gets cha…
cmu-10799-diffusion-flow L5: CMU 10799 S26: Lecture 5 - Flow Matching - Diffusion & Flow Matching 15: 12 two assumptions. >> Uh two assumptions. One is that >> Uh two assumptions. One is that >> Uh two assumptions. One is that add up to one. The second one is that add up to one. The second one is that ad…
cmu-10799-diffusion-flow L5: CMU 10799 S26: Lecture 5 - Flow Matching - Diffusion & Flow Matching 16: 04 thing that like flow out >> as physically inclined. >> as physically inclined. >> as physically inclined. >> It is okay. >> It is okay. >> It is okay. >> I'm just a civil engineer. >> I'm just a civil…
cmu-10799-diffusion-flow L5: CMU 10799 S26: Lecture 5 - Flow Matching - Diffusion & Flow Matching 17: 08 the divergence connection again the divergence connection again >> yes I I think I missed a P here actually >> yes I I think I missed a P here actually >> yes I I think I missed a P here actually by t…
cmu-10799-diffusion-flow L5: CMU 10799 S26: Lecture 5 - Flow Matching - Diffusion & Flow Matching 18: 21 that like so this is the correct that like so this is the correct divergence. Sorry that that that one I divergence. Sorry that that that one I divergence. Sorry that that that one I missed P. Um but …
cmu-10799-diffusion-flow L5: CMU 10799 S26: Lecture 5 - Flow Matching - Diffusion & Flow Matching 19: 13 the log probability of of the log density. Okay. And this OD is actually density. Okay. And this OD is actually density. Okay. And this OD is actually equal to so the derivative of the total equal to …
cmu-10799-diffusion-flow L5: CMU 10799 S26: Lecture 5 - Flow Matching - Diffusion & Flow Matching 20: 52 So exactly so so how do you train your continuous how do you train your continuous how do you train your continuous normalizing flow from here? What do we normalizing flow from here? What do we normal…
cmu-10799-diffusion-flow L5: CMU 10799 S26: Lecture 5 - Flow Matching - Diffusion & Flow Matching 22: 04 we actually need to do numerical integration right. But this is at integration right. But this is at integration right. But this is at training time. So that just means that training time. So that jus…
cmu-10799-diffusion-flow L5: CMU 10799 S26: Lecture 5 - Flow Matching - Diffusion & Flow Matching 23: 07 numerical integration, right? So it still has a lot of steps. Can we do still has a lot of steps. Can we do still has a lot of steps. Can we do something that doesn't require a lot of something that d…
cmu-10799-diffusion-flow L5: CMU 10799 S26: Lecture 5 - Flow Matching - Diffusion & Flow Matching 24: 11 just need to make sure that the velocity actually match with the ground truth actually match with the ground truth actually match with the ground truth velocity. velocity. velocity. So you just do L2 …
cmu-10799-diffusion-flow L5: CMU 10799 S26: Lecture 5 - Flow Matching - Diffusion & Flow Matching 25: 12 changing every day be like actually I think that the the storm is moving north think that the the storm is moving north think that the the storm is moving north or maybe not. We don't know, right? So …
cmu-10799-diffusion-flow L5: CMU 10799 S26: Lecture 5 - Flow Matching - Diffusion & Flow Matching 25: 58 Yeah. That's right. That's right. You just go straight. just go straight. just go straight. Yeah, exactly. Uh so basically this is Yeah, exactly. Uh so basically this is Yeah, exactly. Uh so basically…
cmu-10799-diffusion-flow L5: CMU 10799 S26: Lecture 5 - Flow Matching - Diffusion & Flow Matching 26: 57 just start from some prior which we can just start from some prior which we can choose. So it doesn't matter we can choose. So it doesn't matter we can choose. So it doesn't matter we can choose the p…
cmu-10799-diffusion-flow L5: CMU 10799 S26: Lecture 5 - Flow Matching - Diffusion & Flow Matching 27: 43 the the data point then you can get a marginal marginal marginal uh yeah and also uh just the boundary uh yeah and also uh just the boundary uh yeah and also uh just the boundary condition essentially…
cmu-10799-diffusion-flow L5: CMU 10799 S26: Lecture 5 - Flow Matching - Diffusion & Flow Matching 29: 03 probability path and also just like how probability path and also just like how like and reweed by how likely in general like and reweed by how likely in general like and reweed by how likely in gener…
cmu-10799-diffusion-flow L5: CMU 10799 S26: Lecture 5 - Flow Matching - Diffusion & Flow Matching 30: 38 this average is like averaging by like this average is like averaging by like how likely is the data point given your how likely is the data point given your how likely is the data point given your cu…
cmu-10799-diffusion-flow L5: CMU 10799 S26: Lecture 5 - Flow Matching - Diffusion & Flow Matching 31: 44 regularization condition. This can can can be done. Uh and then uh basically can be done. Uh and then uh basically can be done. Uh and then uh basically you uh input your um because we know you uh inp…
cmu-10799-diffusion-flow L5: CMU 10799 S26: Lecture 5 - Flow Matching - Diffusion & Flow Matching 32: 46 can construct can generate the marginal property path which is what we want. property path which is what we want. property path which is what we want. Oh, I saw so many confusion. Oh, I saw so many co…
cmu-10799-diffusion-flow L5: CMU 10799 S26: Lecture 5 - Flow Matching - Diffusion & Flow Matching 33: 50 Think about that. Isn't that pretty Think about that. Isn't that pretty cool? Okay. Why? Why? Why is that? Okay. cool? Okay. Why? Why? Why is that? Okay. cool? Okay. Why? Why? Why is that? Okay. So, t…
cmu-10799-diffusion-flow L5: CMU 10799 S26: Lecture 5 - Flow Matching - Diffusion & Flow Matching 34: 46 Like basically you if you swap uh the Like basically you if you swap uh the dx1 term inside so you swap the order of dx1 term inside so you swap the order of dx1 term inside so you swap the order of t…
cmu-10799-diffusion-flow L5: CMU 10799 S26: Lecture 5 - Flow Matching - Diffusion & Flow Matching 35: 50 we're compressing the bullet. >> It's literally the same. It's literally >> It's literally the same. It's literally >> It's literally the same. It's literally the same. It's equivalent. It's not even …
cmu-10799-diffusion-flow L5: CMU 10799 S26: Lecture 5 - Flow Matching - Diffusion & Flow Matching 36: 53 Well we first have the the the endpoint distribution and because we're distribution and because we're distribution and because we're transforming it straight to the point transforming it straight to t…
cmu-10799-diffusion-flow L5: CMU 10799 S26: Lecture 5 - Flow Matching - Diffusion & Flow Matching 37: 52 >> Yeah. No no this is what we chose. This is a design choice. So that so this is a design choice. So that so this is a design choice. So that so this thing is generalizable to any kind of thing is ge…
cmu-10799-diffusion-flow L5: CMU 10799 S26: Lecture 5 - Flow Matching - Diffusion & Flow Matching 39: 09 we can directly sample from >> therefor you >> like previous lectures like gausian >> like previous lectures like gausian assumption is used like this closure on assumption is used like this closure o…
cmu-10799-diffusion-flow L5: CMU 10799 S26: Lecture 5 - Flow Matching - Diffusion & Flow Matching 40: 22 we talked about stuff when we u when we actually uh decrease the the velocity at actually uh decrease the the velocity at actually uh decrease the the velocity at which we adding noise. which we addin…
cmu-10799-diffusion-flow L5: CMU 10799 S26: Lecture 5 - Flow Matching - Diffusion & Flow Matching 41: 26 this particular path. Only on this this particular path. Only on this particular x0 to x1 path. But it's not particular x0 to x1 path. But it's not particular x0 to x1 path. But it's not in general. i…
cmu-10799-diffusion-flow L5: CMU 10799 S26: Lecture 5 - Flow Matching - Diffusion & Flow Matching 42: 24 >> because if you look at the if you look >> because if you look at the if you look at the this the the left hand side right at the this the the left hand side right at the this the the left hand side…
cmu-10799-diffusion-flow L5: CMU 10799 S26: Lecture 5 - Flow Matching - Diffusion & Flow Matching 43: 16 literally the same conference and they all got into the same conference. all got into the same conference. all got into the same conference. So yeah, so the first group is a group So yeah, so the firs…
cmu-10799-diffusion-flow L5: CMU 10799 S26: Lecture 5 - Flow Matching - Diffusion & Flow Matching 44: 00 but you may have this question, right? I feel like some people are having this feel like some people are having this feel like some people are having this question but they didn't ask. So like questio…
cmu-10799-diffusion-flow L5: CMU 10799 S26: Lecture 5 - Flow Matching - Diffusion & Flow Matching 44: 58 do is now let's say you you after training with the linear interpolation training with the linear interpolation training with the linear interpolation you already got this coupling. So the you already…
cmu-10799-diffusion-flow L5: CMU 10799 S26: Lecture 5 - Flow Matching - Diffusion & Flow Matching 45: 50 right? So you can map from one point in right? So you can map from one point in P 0 to another point in P1 and then you P 0 to another point in P1 and then you P 0 to another point in P1 and then you …
cmu-10799-diffusion-flow L5: CMU 10799 S26: Lecture 5 - Flow Matching - Diffusion & Flow Matching 46: 34 because you don't know like basically if you if you only do one step there can be you if you only do one step there can be you if you only do one step there can be like a lot of um uh uh like like lik…
cmu-10799-diffusion-flow L5: CMU 10799 S26: Lecture 5 - Flow Matching - Diffusion & Flow Matching 47: 37 >> The third image is the linear >> The third image is the linear interpolation of the new coupling. interpolation of the new coupling. interpolation of the new coupling. >> That what is that doing? >…
cmu-10799-diffusion-flow L5: CMU 10799 S26: Lecture 5 - Flow Matching - Diffusion & Flow Matching 48: 17 connected this side to that side and connected this side to that side and that side to this side. There's no that side to this side. There's no that side to this side. There's no there's no this anymo…
cmu-10799-diffusion-flow L5: CMU 10799 S26: Lecture 5 - Flow Matching - Diffusion & Flow Matching 48: 56 perfectly trained into this process, >> then you do it again. Yeah. Yeah. So, >> then you do it again. Yeah. Yeah. So, >> then you do it again. Yeah. Yeah. So, this is just you you get it this is just…
cmu-10799-diffusion-flow L5: CMU 10799 S26: Lecture 5 - Flow Matching - Diffusion & Flow Matching 49: 44 well. you're just like kind of random random walking a little bit. Whereas for random walking a little bit. Whereas for random walking a little bit. Whereas for flow matching, you don't really do flow…
cmu-10799-diffusion-flow L5: CMU 10799 S26: Lecture 5 - Flow Matching - Diffusion & Flow Matching 50: 27 question is is flow matching also the question is is flow matching also the same thing because if you think about it same thing because if you think about it same thing because if you think about it y…
cmu-10799-diffusion-flow L5: CMU 10799 S26: Lecture 5 - Flow Matching - Diffusion & Flow Matching 51: 12 can write everything as if it is flow can write everything as if it is flow matching as well and then you can matching as well and then you can matching as well and then you can actually just recover …
cmu-10799-diffusion-flow L5: CMU 10799 S26: Lecture 5 - Flow Matching - Diffusion & Flow Matching 52: 03 still need to take care of that part. But it turns out that we actually do But it turns out that we actually do But it turns out that we actually do know how to take care of that part. And know how to…
cmu-10799-diffusion-flow L5: CMU 10799 S26: Lecture 5 - Flow Matching - Diffusion & Flow Matching 52: 44 OD, right? So this is the just um say we OD, right? So this is the just um say we have this particular OD and it turns out have this particular OD and it turns out have this particular OD and it turns…
cmu-10799-diffusion-flow L5: CMU 10799 S26: Lecture 5 - Flow Matching - Diffusion & Flow Matching 53: 30 change for the probability means that the marginalss are all the same. So this the marginalss are all the same. So this the marginalss are all the same. So this just means that now if you have your ju…
cmu-10799-diffusion-flow L5: CMU 10799 S26: Lecture 5 - Flow Matching - Diffusion & Flow Matching 54: 36 >> That's a great question. Um so for >> That's a great question. Um so for example, I don't know if you guys example, I don't know if you guys example, I don't know if you guys familiar with the RL. …
cmu-10799-diffusion-flow L5: CMU 10799 S26: Lecture 5 - Flow Matching - Diffusion & Flow Matching 55: 40 Use the use the corresponding PF OD of Use the use the corresponding PF OD of the SDE. Right? So you just plug it in the SDE. Right? So you just plug it in the SDE. Right? So you just plug it in and t…
cmu-10799-diffusion-flow L5: CMU 10799 S26: Lecture 5 - Flow Matching - Diffusion & Flow Matching 57: 07 >> A lot of uh uh lot of PD getting converted to OD. Is it are we just doing converted to OD. Is it are we just doing converted to OD. Is it are we just doing it because it's simpler or do we you it b…
cmu-10799-diffusion-flow L5: CMU 10799 S26: Lecture 5 - Flow Matching - Diffusion & Flow Matching 57: 53 diversity but but yes so like essentially um if you're sampling from a essentially um if you're sampling from a essentially um if you're sampling from a SDE then it's going to be yeah because SDE then…
cmu-10799-diffusion-flow L5: CMU 10799 S26: Lecture 5 - Flow Matching - Diffusion & Flow Matching 59: 06 sampling chain through your by by by sampling chain through your by by by backward integrating your velocity and backward integrating your velocity and backward integrating your velocity and then duri…
cmu-10799-diffusion-flow L5: CMU 10799 S26: Lecture 5 - Flow Matching - Diffusion & Flow Matching 60: 12 you know just like you know you just add something divide something you it's the something divide something you it's the something divide something you it's the same thing. Okay. same thing. Okay. sam…
cmu-10799-diffusion-flow L5: CMU 10799 S26: Lecture 5 - Flow Matching - Diffusion & Flow Matching 61: 01 next week we're gonna be able to see like like like uh different options to further uh different options to further uh different options to further improve what we have learned. Um so for improve what…
cmu-10799-diffusion-flow L5: CMU 10799 S26: Lecture 5 - Flow Matching - Diffusion & Flow Matching 61: 41 the generation faster? And we're going to learn uh to do it with or without to learn uh to do it with or without to learn uh to do it with or without training retraining of the model. And training ret…
diffusion-principles-vizuara L2: Lecture 9 - Introduction to Flow Models | Principles of Diffusion Models 00: 03 Good morning everyone. Good morning everyone. Today we are starting with the next Today we are starting with the next Today we are starting with the next lecture of our course which is lecture of our …
diffusion-principles-vizuara L2: Lecture 9 - Introduction to Flow Models | Principles of Diffusion Models 01: 10 simple which you could have got in the simple which you could have got in the first lecture itself. first lecture itself. first lecture itself. But I don't want to show you that route But I don't want…
diffusion-principles-vizuara L2: Lecture 9 - Introduction to Flow Models | Principles of Diffusion Models 02: 06 keep the mathematics as simple as possible [snorts] and I have taken possible [snorts] and I have taken possible [snorts] and I have taken inspiration from an uh MIT course to inspiration from an uh M…
diffusion-principles-vizuara L2: Lecture 9 - Introduction to Flow Models | Principles of Diffusion Models 03: 01 model is a representation of a phenomena a neural network is an example of a a neural network is an example of a a neural network is an example of a model or any mathematical function which model or a…
diffusion-principles-vizuara L2: Lecture 9 - Introduction to Flow Models | Principles of Diffusion Models 04: 22 we have looked at different techniques to solve this broader problem. It to solve this broader problem. It to solve this broader problem. It started out with variational started out with variational s…
diffusion-principles-vizuara L2: Lecture 9 - Introduction to Flow Models | Principles of Diffusion Models 05: 34 one of the most consequential techniques in modern [snorts] in modern [snorts] in modern [snorts] generative modeling. And the reason it generative modeling. And the reason it generative modeling. And…
diffusion-principles-vizuara L2: Lecture 9 - Introduction to Flow Models | Principles of Diffusion Models 06: 33 and it works exceptionally well. You can see here they have this action expert see here they have this action expert see here they have this action expert and this action expert is built [snorts] and …
diffusion-principles-vizuara L2: Lecture 9 - Introduction to Flow Models | Principles of Diffusion Models 07: 26 formula comes about which is very simple. So flow modeling at the heart of simple. So flow modeling at the heart of simple. So flow modeling at the heart of it is very simple and it has huge number it…
diffusion-principles-vizuara L2: Lecture 9 - Introduction to Flow Models | Principles of Diffusion Models 08: 45 maybe you're sitting on a table right maybe you're sitting on a table right now or you have a table in front of you. now or you have a table in front of you. now or you have a table in front of you. U…
diffusion-principles-vizuara L2: Lecture 9 - Introduction to Flow Models | Principles of Diffusion Models 09: 51 with time. So the magnets that we have placed on the table, what if these placed on the table, what if these placed on the table, what if these magnets are constantly moving? magnets are constantly mo…
diffusion-principles-vizuara L2: Lecture 9 - Introduction to Flow Models | Principles of Diffusion Models 10: 59 take at multiple time steps and hence you will get a vector field which is you will get a vector field which is you will get a vector field which is changing with time. So now we are discussing time d…
diffusion-principles-vizuara L2: Lecture 9 - Introduction to Flow Models | Principles of Diffusion Models 12: 12 depends on not just the position in space but also it depends on the time space but also it depends on the time space but also it depends on the time snapshot. So it is a timed dependent snapshot. So …
diffusion-principles-vizuara L2: Lecture 9 - Introduction to Flow Models | Principles of Diffusion Models 13: 07 timed dependent vector field. So another way of defining this is So another way of defining this is So another way of defining this is people usually write this t as a people usually write this t as a…
diffusion-principles-vizuara L2: Lecture 9 - Introduction to Flow Models | Principles of Diffusion Models 14: 11 So for example, if we take this example at at the top at time t equal to0, this at at the top at time t equal to0, this at at the top at time t equal to0, this is what my velocity field looks like. is…
diffusion-principles-vizuara L2: Lecture 9 - Introduction to Flow Models | Principles of Diffusion Models 15: 16 So now we are asking the question how do the position of particles which are the position of particles which are the position of particles which are inside the space change according to inside the spa…
diffusion-principles-vizuara L2: Lecture 9 - Introduction to Flow Models | Principles of Diffusion Models 16: 24 particle if I know the velocity vector field. This is exactly what this formula field. This is exactly what this formula field. This is exactly what this formula says. says. says. So if I have a parti…
diffusion-principles-vizuara L2: Lecture 9 - Introduction to Flow Models | Principles of Diffusion Models 17: 59 of x0 okay so now this if I write as delta x okay so now this if I write as delta x okay so now this if I write as delta x by delta t by delta t by delta t is equal to mu of u of x0. is equal to mu of…
diffusion-principles-vizuara L2: Lecture 9 - Introduction to Flow Models | Principles of Diffusion Models 19: 08 box end up at time t equal to 10 let's box end up at time t equal to 10 let's say. Now if you know the exact velocity say. Now if you know the exact velocity say. Now if you know the exact velocity at…
diffusion-principles-vizuara L2: Lecture 9 - Introduction to Flow Models | Principles of Diffusion Models 20: 02 box follows the vector field and the box follows the vector field and the question I'm trying to address is where question I'm trying to address is where question I'm trying to address is where does t…
diffusion-principles-vizuara L2: Lecture 9 - Introduction to Flow Models | Principles of Diffusion Models 21: 06 they represent the vector field which is time dependent. That is why the arrows time dependent. That is why the arrows time dependent. That is why the arrows are changing with time. And if we know are…
diffusion-principles-vizuara L2: Lecture 9 - Introduction to Flow Models | Principles of Diffusion Models 22: 21 but it is not quite correct because at but it is not quite correct because at the end of it we are doing an the end of it we are doing an the end of it we are doing an approximation. approximation. ap…
diffusion-principles-vizuara L2: Lecture 9 - Introduction to Flow Models | Principles of Diffusion Models 23: 38 everywhere in a lot of papers. But flow everywhere in a lot of papers. But flow means something very specific. In our means something very specific. In our means something very specific. In our mind, …
diffusion-principles-vizuara L2: Lecture 9 - Introduction to Flow Models | Principles of Diffusion Models 24: 34 flow is a collection of trajectories which evolve according to the velocity which evolve according to the velocity which evolve according to the velocity field. We have just seen that if we know field…
diffusion-principles-vizuara L2: Lecture 9 - Introduction to Flow Models | Principles of Diffusion Models 25: 30 now let us look at one single snapshot because we have we have restricted with because we have we have restricted with because we have we have restricted with the screen in in front of us. Now you the…
diffusion-principles-vizuara L2: Lecture 9 - Introduction to Flow Models | Principles of Diffusion Models 26: 21 trajectories and we get a overall sense of the flow. You can see that this this of the flow. You can see that this this of the flow. You can see that this this is probably something which is swirling.…
diffusion-principles-vizuara L2: Lecture 9 - Introduction to Flow Models | Principles of Diffusion Models 27: 09 let's let's see how the grid deforms. Now note that the grid is going to Now note that the grid is going to Now note that the grid is going to deform in a way that the vector field deform in a way tha…
diffusion-principles-vizuara L2: Lecture 9 - Introduction to Flow Models | Principles of Diffusion Models 28: 09 according to a trajectory which is governed by an ordinary differential governed by an ordinary differential governed by an ordinary differential equation and if we collect all these equation and if w…
diffusion-principles-vizuara L2: Lecture 9 - Introduction to Flow Models | Principles of Diffusion Models 29: 26 understand how the grid deforms. Yeah. So this this does work. So this this does work. So this this does work. Okay. So you can actually change these Okay. So you can actually change these Okay. So yo…
diffusion-principles-vizuara L2: Lecture 9 - Introduction to Flow Models | Principles of Diffusion Models 30: 34 using the word vector field also. Second is the trajectories which are calculated is the trajectories which are calculated is the trajectories which are calculated from the velocity field using the si…
diffusion-principles-vizuara L2: Lecture 9 - Introduction to Flow Models | Principles of Diffusion Models 31: 46 It is only one dimensional minus theta x and it is independent of time. So at and it is independent of time. So at and it is independent of time. So at every time snapshot you take a camera every time…
diffusion-principles-vizuara L2: Lecture 9 - Introduction to Flow Models | Principles of Diffusion Models 32: 52 is dxt by dt is equal to minus theta of xt. xt. xt. Now let's see if this is indeed the Now let's see if this is indeed the Now let's see if this is indeed the flow. flow. If we substitute this in xt,…
diffusion-principles-vizuara L2: Lecture 9 - Introduction to Flow Models | Principles of Diffusion Models 34: 06 is itself completely zero. So the position stays zero. But position stays zero. But position stays zero. But let's look at yeah if x0 is any any any let's look at yeah if x0 is any any any let's look …
diffusion-principles-vizuara L2: Lecture 9 - Introduction to Flow Models | Principles of Diffusion Models 35: 12 example x0 into e to minus theta t and we get the exact same plot. and we get the exact same plot. So we can actually play this and see how So we can actually play this and see how So we can actually …
diffusion-principles-vizuara L2: Lecture 9 - Introduction to Flow Models | Principles of Diffusion Models 36: 03 field and how the flow is a collection of the trajectories. of the trajectories. of the trajectories. [snorts] Okay. Now uh once we are getting Okay. Now uh once we are getting confident with the defi…
diffusion-principles-vizuara L2: Lecture 9 - Introduction to Flow Models | Principles of Diffusion Models 37: 06 We take small steps in the direction of the velocity field and we see how the the velocity field and we see how the the velocity field and we see how the particle trajectory changes with time. particl…
diffusion-principles-vizuara L2: Lecture 9 - Introduction to Flow Models | Principles of Diffusion Models 37: 56 long is your simulation carried on. Okay. So we initialize time as t equal Okay. So we initialize time as t equal Okay. So we initialize time as t equal to0. The step size which is delta t is 1 to0. T…
diffusion-principles-vizuara L2: Lecture 9 - Introduction to Flow Models | Principles of Diffusion Models 38: 56 position. That is all is mentioned in the flowchart. So basically the flowchart. So basically the flowchart. So basically if we have a particle and if we know the if we have a particle and if we know …
diffusion-principles-vizuara L2: Lecture 9 - Introduction to Flow Models | Principles of Diffusion Models 39: 45 For example, when we are using flow models for robotics or protein models for robotics or protein models for robotics or protein synthesis, synthesis, synthesis, people calculate the flow which is the…
diffusion-principles-vizuara L2: Lecture 9 - Introduction to Flow Models | Principles of Diffusion Models 40: 49 Now we have defined the word flow in the Now we have defined the word flow in the initial part of the lecture. We will initial part of the lecture. We will initial part of the lecture. We will underst…
diffusion-principles-vizuara L2: Lecture 9 - Introduction to Flow Models | Principles of Diffusion Models 41: 41 So this is exactly what we are going to So this is exactly what we are going to do in flow models. Also our goal is to do in flow models. Also our goal is to do in flow models. Also our goal is to con…
diffusion-principles-vizuara L2: Lecture 9 - Introduction to Flow Models | Principles of Diffusion Models 43: 05 So we use the same ordinary differential So we use the same ordinary differential equation dx by dt is equal to u. But equation dx by dt is equal to u. But equation dx by dt is equal to u. But this ti…
diffusion-principles-vizuara L2: Lecture 9 - Introduction to Flow Models | Principles of Diffusion Models 43: 58 we have added in flow model is that the we have added in flow model is that the collection of these particles represent collection of these particles represent collection of these particles represent …
diffusion-principles-vizuara L2: Lecture 9 - Introduction to Flow Models | Principles of Diffusion Models 44: 54 evolves from t =0 to t = 1. evolves from t =0 to t = 1. So this is sort of what we want. We want So this is sort of what we want. We want So this is sort of what we want. We want to start from the ini…
diffusion-principles-vizuara L2: Lecture 9 - Introduction to Flow Models | Principles of Diffusion Models 45: 57 the start distribution which is a simple gshian. It is uniformly distributed. gshian. It is uniformly distributed. gshian. It is uniformly distributed. There are maybe around 2,000 particles There are…
diffusion-principles-vizuara L2: Lecture 9 - Introduction to Flow Models | Principles of Diffusion Models 46: 47 from the start distribution to the end distribution. Now here there are a lot of options. We Now here there are a lot of options. We can convert can convert can convert we can change the end distribut…
diffusion-principles-vizuara L2: Lecture 9 - Introduction to Flow Models | Principles of Diffusion Models 47: 42 replaced by a neural network. replaced by a neural network. So there is another word for this in So there is another word for this in So there is another word for this in literature which is also call…
diffusion-principles-vizuara L2: Lecture 9 - Introduction to Flow Models | Principles of Diffusion Models 48: 29 model is being trained and the loss is going down. What is the meaning of this going down. What is the meaning of this going down. What is the meaning of this statement? The flow model is going to be …
diffusion-principles-vizuara L2: Lecture 9 - Introduction to Flow Models | Principles of Diffusion Models 49: 25 see the animation over here once this code runs. Yeah. So let's see uh as expected we Yeah. So let's see uh as expected we start with the initial gshian start with the initial gshian start with the in…
diffusion-principles-vizuara L2: Lecture 9 - Introduction to Flow Models | Principles of Diffusion Models 50: 30 models we had a number of encoders and a number of decoders. number of decoders. number of decoders. So they were discrete. Here something a So they were discrete. Here something a So they were discre…
diffusion-principles-vizuara L2: Lecture 9 - Introduction to Flow Models | Principles of Diffusion Models 52: 03 the particles who are compressing inside here they are moving out and here they are moving out and here they are moving out and slowly resembling that spiral shape. So slowly resembling that spiral sh…
diffusion-principles-vizuara L2: Lecture 9 - Introduction to Flow Models | Principles of Diffusion Models 52: 56 initial problem of converting the uh initial problem of converting the uh gshian distribution to our actual gshian distribution to our actual gshian distribution to our actual distribution. What we sa…
diffusion-principles-vizuara L2: Lecture 9 - Introduction to Flow Models | Principles of Diffusion Models 53: 50 So the differential equation is also termed as a neural ordinary differential termed as a neural ordinary differential termed as a neural ordinary differential equation. So the terms that I have equat…
diffusion-principles-vizuara L2: Lecture 9 - Introduction to Flow Models | Principles of Diffusion Models 54: 43 ends our first lecture and in the next ends our first lecture and in the next lecture we will understand what is the lecture we will understand what is the lecture we will understand what is the targe…