Pi-Flow Policy-Based Few-Step Generation via Imitation Distillation

Chen et al. 2026



Hozy Summary




Setup & Model

Setups) Flow Matching Model

  • \(p(x_0)\) : the (latent) data probability density for a datapoint \(x_0\in\mathbb{R}^D\)
  • \(x_t = \alpha_t x_0 + \sigma_t \epsilon\) : the diffused noisy data
    • where
      • \(t\in(0,1],\; \epsilon\sim\mathcal{N}(\mathbf{0,I}),\; \alpha_t = 1-t,\; \sigma_t = t\).
    • cf.)
      • Marginal Density : \(\displaystyle p(x_t) = \int_{\mathbb{R}^D}\mathcal{N}\left(x_t;\;\alpha_t x_0, \sigma_t^2\mathbf{I}\right)p(x_0)\text{d}x_0\)
      • Optimal transport map via probability flow ODE
      • \(\displaystyle\frac{\text{d}x_t}{\text{d}t} = \dot{x}_t = \frac{x_t - \mathbb{E}_{x_0\sim p(x_0\mid x_t)}[x_0]}{t} = \frac{x_t - \int_{\mathbb{R}^D}x_0p(x_0\mid x_t)\text{d}x_0}{t}\).
        • with the denoising posterior \(p(x_0\mid x_t) := \displaystyle\frac{\mathcal{N}\left(x_t;\;\alpha_t x_0, \sigma_t^2\mathbf{I}\right) p(x_0)}{p(x_t)}\)
  • Objective
    • \(\displaystyle\mathcal{L}_\theta = \mathbb{E}_{t, x_0, x_t}\left[\frac{1}{2}\Vert u - G_\theta(x_t,t) \Vert^2\right]\) with sample velocity of \(\displaystyle u :=\frac{x_t-x_0}{t}\)
      • for a neural network \(G_\theta(x_t, t)\) with learnable parameters



Model) pi-Flow: Policy-Based Few-Step Generation

  • Def.)
    • \(\pi:\mathbb{R}^D\times\mathbb{R}\rightarrow\mathbb{R}^D\) : a network-free policy function that maps a state \((x_t, t)\) to a flow velocity
      • Requirement for being network-free
        • \(\pi\) needs to describe a single ODE trajectory fully determined by its initial state \((x_{t_{\text{src}}}, t_{\text{src}})\)
  • Training)
    • Adapt a flow model to output the entire dynamic policy that governs the full trajectory
      • i.e.) For the policy function space \(\mathcal{F}:=\left\{\pi:\mathbb{R}^D\times\mathbb{R}\rightarrow\mathbb{R}^D\right\}\) train a policy generator network \(G_\phi:\mathbb{R}^D\times\mathbb{R}\rightarrow\mathcal{F}\)
  • Two-step Sampling)
    1. Single Policy Generation Step
      • Given the initial state \((x_{t_{\text{src}}}, t_{\text{src}})\), sample a policy \(\pi\leftarrow G_\phi(x_{t_{\text{src}}}, t_{\text{src}})\)
    2. Multiple Policy Integration Substeps
      • Integrate the ODE by querying policy velocity over multiple steps
        • \(\displaystyle x_{t_{\text{dst}}} \leftarrow x_{t_{\text{src}}} + \int_{t_{\text{src}}}^{t_{\text{dst}}} \pi(x_t, t) \text{d}t\).
  • Props.)
    • Decouples network evaluation steps from the ODE integration substeps.
      • Advantages)
        • Few network evaluation for generation
        • Capable of following well-established imitation learning (IL) approaches to directly match the policy velocity \(\pi(x_t, t)\) to the teacher velocity \(G_\theta(x_t, t)\).
          • How?) It can execute dense integration substeps like standard flow matching teacher.



3. Policy Generation

3.1 Dynamic-x_0 policy (DX)

  • Def.)
    • \(\pi(x_t, t) := \displaystyle\frac{x_t - \hat{x}_{0}^{(t)}}{t}\) where \(\hat{x}_{0}^{(t)}\) approximates the posterior moment \(\mathbb{E}_{x_0\sim p(x_0\mid x_t)[x_0]}\)
  • Model)
    • For evenly spaced times \(t_1,\ldots,t_N\in[t_\text{dst}, t_{src}]\),
      • set a grid of \(\hat{x}_0^{(t_i)}\;(i=1,\ldots,N)\)
    • Expand the output of \(G_\phi(x_{t_{src}}, t_{src}) = u\) to \(x_0\in\mathbb{R}^N\) using the \(u\text{-to-}x_0\) reparameterization.
    • Predict \(\hat{x}_0^{(t_i)}\;(i=1,\ldots,N)\) by a single evaluation of the student network \(G_\phi(x_{t_{src}}, t_{src})\).
    • Obtain \(\hat{x}_0^{(t)}\) for \(t\in[t_{\text{dst}}, t_{\text{src}}]\) using the linear interpolation.
  • Props.)
    • The posterior moment depends only on \(t\).
    • Fast and expressive (we may choose any \(N\))
    • Limited robustness because \(\hat{x}_{0}^{(t)}\) is not adaptive to perturbations in \(x_t\).


3.2 GMFlow Policy

  • Motivation)
    • Stronger robustness!
  • Idea)
    • GM Flow
      • Expand the network output channels to predict a factorized Gaussian mixture (GM) velocity distribution \(q(u\mid x_{t_{\text{src}}}) = \displaystyle\prod_{i=1}^L\sum_{k=1}^K A_{ik}\mathcal{N}\left( u_i; \mu_{ik}, s^2\mathbf{I} \right)\)
        • for
          • hyperparameters
            • \(L\) : sequence length
            • \(C\) : channel size
            • \(K\) : a hyperparameter specifying the number of mixture components
          • GM parameters predicted by network \(G_\phi\)
            • \(A_{ik}\in\mathbb{R}_+\),
            • \(\mu_{ik}\in\mathbb{R}^C\),
            • \(s\in\mathbb{R}_+\),
        • i.e.) The student network \(G_\phi\) maps the initial state \(x_{t_{\text{src}}}\) to multiple denoising modes that parameterize the GMFlow policy.
      • This GMFlow policy enables a closed-form velocity expression at future state \((x_t, t),\;\forall 0\lt t\lt t_{\text{src}}\) described by
        • \(q(x_0\mid x_{t_{\text{src}}}) = \displaystyle\sum_{k=1}^K A_k'\mathcal{N}\left(x_0;\; \mu_k', s'^2\mathbf{I}\right)\).
Derivation from Appendix F
  • Model)
    • Policy function \(\pi:\mathbb{R}^C\times\mathbb{R}\rightarrow\mathbb{R}^C\) is given by
      \(\begin{aligned} \pi(x_t, t) &= \frac{x_t-\mathbb{E}_{x_0\sim q(x_0\mid x_t)}[x_0]}{t} \\ &= \frac{x_t-\sum_{k=1}^K A_k' \mu_k'}{t} \end{aligned}\)



4. Policy-based Image Distillation (π-ID)

  • Idea)
    • DAgger-style on-policy imitation
  • Settings)
    • \(\text{NFE}\) : the number of evaluation
      • Then the \(\text{NFE}\)-number of intervals will be set as \([0, \frac{1}{\text{NFE}}], [\frac{1}{\text{NFE}}, \frac{2}{\text{NFE}}], \ldots, [\frac{\text{NFE}-1}{\text{NFE}}, 1]\)
    • \(G_\theta\) : pre-trained teacher
    • \(G_\phi\) : student
    • \(c\) : condition
  • Training)
    • Sample \(t_\text{src}\sim\left\{ \frac{1}{\text{NFE}}, \frac{2}{\text{NFE}}, \ldots, 1 \right\}\)
      • i.e.) the interval will be \(\left[t_\text{src}-\frac{1}{\text{NFE}}, t_\text{src}\right]\) with \(t_{\text{dst}}=t_\text{src}-\frac{1}{\text{NFE}}\)
    • Initialize \(x_{t_\text{src}}\)
    • Get
      • \(\pi\leftarrow G_\phi(x_{t_\text{src}}, t_\text{src}, c)\),
      • \(\pi_D\leftarrow \text{stopgrad}(\pi)\).
    • For \(t\sim\mathcal{U}(t_\text{src}-\frac{1}{\text{NFE}}, t_\text{src})\)
      • \(x_t\leftarrow x_{t_\text{src}} + \displaystyle\int_{t_\text{src}}^t \pi_D(x_s, s)\text{d}s\) : student roll out
        • cf.) Authors mentioned small substep size of 1/128.
      • \(\mathcal{L}_\phi\leftarrow\mathcal{L}_\phi + \displaystyle\frac{1}{2}\Vert G_\theta(x_t, t, c) - \pi(x_t ,t)\Vert^2\) : \(\ell_2\)-loss with the teacher query and the student output
    • Optimize \(\phi\leftarrow\text{Adam}(\phi, \nabla_\phi\mathcal{L}_\phi)\).


4.1 Data-dependent on-policy π-ID

4.2 Data-free on-policy π-ID




Enjoy Reading This Article?

Here are some more articles you might like to read next:

  • Flow Straight and Fast - Learning to Generate and Transfer Data with Rectified Flow (Rectified Flow)
  • (DM Reconst.) Ch.2 Variational Perspective - From VAEs to DDPM
  • Flow Matching for Generative Modeling (CFM)
  • Scaling Rectified Flow Transformers for High-Resolution Image Synthesis (Stable Diffusion 3)
  • (Presentation PDF) Video Models are Zero-shot Learners and Reasoners