MixFlow: Mixed Source Distributions Improve Rectified Flows

• URL: http://arxiv.org/abs/2604.09181v1
• Date: Fri, 10 Apr 2026 10:06:15 GMT
• Title: MixFlow: Mixed Source Distributions Improve Rectified Flows
• Abstract summary: Diffusion models and their variations, such as rectified flows, generate diverse and high-quality images.<n>They are hindered by slow iterative sampling caused by the highly curved generative paths they learn.<n>We present MixFlow, a training strategy that reduces the generative path curvatures and considerably improves sampling efficiency.
• Score: 18.451270798004344
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Diffusion models and their variations, such as rectified flows, generate diverse and high-quality images, but they are still hindered by slow iterative sampling caused by the highly curved generative paths they learn. An important cause of high curvature, as shown by previous work, is independence between the source distribution (standard Gaussian) and the data distribution. In this work, we tackle this limitation by two complementary contributions. First, we attempt to break away from the standard Gaussian assumption by introducing $κ\texttt{-FC}$, a general formulation that conditions the source distribution on an arbitrary signal $κ$ that aligns it better with the data distribution. Then, we present MixFlow, a simple but effective training strategy that reduces the generative path curvatures and considerably improves sampling efficiency. MixFlow trains a flow model on linear mixtures of a fixed unconditional distribution and a $κ\texttt{-FC}$-based distribution. This simple mixture improves the alignment between the source and data, provides better generation quality with less required sampling steps, and accelerates the training convergence considerably. On average, our training procedure improves the generation quality by 12\% in FID compared to standard rectified flow and 7\% compared to previous baselines under a fixed sampling budget. Code available at: $\href{https://github.com/NazirNayal8/MixFlow}{https://github.com/NazirNayal8/MixFlow}$

Related papers

• Heavy-Tailed Flow Matching via Random Clocks [52.78194016835051]
  Heavy-tailed data arise in many domains where rare events carry disproportionate importance, such as imbalanced image datasets, financial returns, and weather extremes.<n>We propose Heavy-Tailed Flow Matching via Random Clocks (HTFM), a framework that portrays heavy-tailed sources as mixtures of clock-conditioned Gaussian sources.
  arXiv  Detail & Related papers  (2026-07-15T13:48:05Z)
• Simplifying Flow Matching Transformations with Low-Rank Mixture Models [58.797704398690165]
  We propose using mixtures of probabilistic principal component analyzers (MPPCA) as the latent density for normalizing flows.<n>We simplify the learned flow transformation by learning a latent distribution that more closely aligns with the data distribution in terms of KL divergence.<n>MPPCA models can be fit quickly and cheaply using the expectation-maximization algorithm, making them a practical choice for initializing latent distributions even in high-dimensional generative tasks.
  arXiv  Detail & Related papers  (2026-06-29T03:03:06Z)
• FastMix: Fast Data Mixture Optimization via Gradient Descent [55.109758242985556]
  Fastmix is a novel framework that automates data mixture discovery while training only a single proxy model.<n>We show that optimizing mixture ratios is mathematically equivalent to assigning per-source loss weights under uniform source sampling.<n>FASTmix outperforms baselines while drastically reducing search cost across pre-intensive and post-training.
  arXiv  Detail & Related papers  (2026-06-12T21:46:57Z)
• One-Step Generative Modeling via Wasserstein Gradient Flows [56.266175641614986]
  W-Flow is a framework for training a generator that transforms samples from a simple reference distribution into samples from a target data distribution in a single step.<n>We set a new state of the art for one-step ImageNet 256$times$256 generation, achieving 1.29 FID, with improved mode coverage and domain transfer.
  arXiv  Detail & Related papers  (2026-05-12T08:29:44Z)
• Gaussian Mixture Flow Matching Models [63.092956669059824]
  Diffusion models approximate the denoising distribution as a Gaussian and predict its mean, whereas flow matching models re parameterize the Gaussian mean as flow velocity.<n>They underperform in few-step sampling due to discretization error and tend to produce over-saturated colors under classifier-free guidance (CFG)<n>We introduce a novel probabilistic guidance scheme that mitigates the over-saturation issues of CFG and improves image generation quality.
  arXiv  Detail & Related papers  (2025-04-07T17:59:42Z)
• Boundary-aware Decoupled Flow Networks for Realistic Extreme Rescaling [49.215957313126324]
  Recently developed generative methods, including invertible rescaling network (IRN) based and generative adversarial network (GAN) based methods, have demonstrated exceptional performance in image rescaling. However, IRN-based methods tend to produce over-smoothed results, while GAN-based methods easily generate fake details. We propose Boundary-aware Decoupled Flow Networks (BDFlow) to generate realistic and visually pleasing results.
  arXiv  Detail & Related papers  (2024-05-05T14:05:33Z)
• MGF: Mixed Gaussian Flow for Diverse Trajectory Prediction [72.70572835589158]
  We propose constructing a mixed Gaussian prior for a normalizing flow model for trajectory prediction.<n>Our method achieves state-of-the-art performance in the evaluation of both trajectory alignment and diversity on the popular UCY/ETH and SDD datasets.
  arXiv  Detail & Related papers  (2024-02-19T15:48:55Z)
• MixFlows: principled variational inference via mixed flows [15.723555563232498]
  MixFlows are a new variational family that consists of a mixture of repeated applications of a map to an initial reference distribution.<n>We show that MixFlows have MCMC-like convergence guarantees when the flow map is ergodic and measure-preserving.<n>We also develop an implementation of MixFlows based on uncorrected discretized Hamiltonian dynamics combined with deterministic momentum refreshment.
  arXiv  Detail & Related papers  (2022-05-16T06:57:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.