PairFlow: Closed-Form Source-Target Coupling for Few-Step Generation in Discrete Flow Models

• URL: http://arxiv.org/abs/2512.20063v1
• Date: Tue, 23 Dec 2025 05:31:56 GMT
• Title: PairFlow: Closed-Form Source-Target Coupling for Few-Step Generation in Discrete Flow Models
• Authors: Mingue Park, Jisung Hwang, Seungwoo Yoo, Kyeongmin Yeo, Minhyuk Sung,
• Abstract summary: $texttPairFlow$ is a lightweight preprocessing step for training Discrete Flow Models (DFMs)<n>DFMs suffer from slow sampling due to their iterative nature.<n>$texttPairFlow$ matches or even surpasses the performance of two-stage training involving finetuning.
• Score: 24.911180095603658
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We introduce $\texttt{PairFlow}$, a lightweight preprocessing step for training Discrete Flow Models (DFMs) to achieve few-step sampling without requiring a pretrained teacher. DFMs have recently emerged as a new class of generative models for discrete data, offering strong performance. However, they suffer from slow sampling due to their iterative nature. Existing acceleration methods largely depend on finetuning, which introduces substantial additional training overhead. $\texttt{PairFlow}$ addresses this issue with a lightweight preprocessing step. Inspired by ReFlow and its extension to DFMs, we train DFMs from coupled samples of source and target distributions, without requiring any pretrained teacher. At the core of our approach is a closed-form inversion for DFMs, which allows efficient construction of paired source-target samples. Despite its extremely low cost, taking only up to 1.7% of the compute needed for full model training, $\texttt{PairFlow}$ matches or even surpasses the performance of two-stage training involving finetuning. Furthermore, models trained with our framework provide stronger base models for subsequent distillation, yielding further acceleration after finetuning. Experiments on molecular data as well as binary and RGB images demonstrate the broad applicability and effectiveness of our approach.

Related papers

• TwinFlow: Realizing One-step Generation on Large Models with Self-adversarial Flows [25.487712175353035]
  We propose TwinFlow, a framework for training 1-step generative models.<n>Our method achieves a GenEval score of 0.83 in 1-NFE on text-to-image tasks.<n>Our approach matches the performance of the original 100-NFE model on GenEval and DPG-Bench benchmarks.
  arXiv  Detail & Related papers  (2025-12-03T07:45:46Z)
• Joint Distillation for Fast Likelihood Evaluation and Sampling in Flow-based Models [100.28111930893188]
  Some of today's best generative models still require hundreds to thousands of neural function evaluations to compute a single likelihood.<n>We present fast flow joint distillation (F2D2), a framework that simultaneously reduces the number of NFEs required for both sampling and likelihood evaluation by two orders of magnitude.<n>F2D2 is modular, compatible with existing flow-based few-step sampling models, and requires only an additional divergence prediction head.
  arXiv  Detail & Related papers  (2025-12-02T10:48:20Z)
• Improving Progressive Generation with Decomposable Flow Matching [50.63174319509629]
  Decomposable Flow Matching (DFM) is a simple and effective framework for the progressive generation of visual media.<n>On Imagenet-1k 512px, DFM achieves 35.2% improvements in FDD scores over the base architecture and 26.4% over the best-performing baseline.
  arXiv  Detail & Related papers  (2025-06-24T17:58:02Z)
• Taming Flow Matching with Unbalanced Optimal Transport into Fast Pansharpening [10.23957420290553]
  We propose the Optimal Transport Flow Matching framework to achieve one-step, high-quality pansharpening.<n>The OTFM framework enables simulation-free training and single-step inference while maintaining strict adherence to pansharpening constraints.
  arXiv  Detail & Related papers  (2025-03-19T08:10:49Z)
• Adding Conditional Control to Diffusion Models with Reinforcement Learning [68.06591097066811]
  Diffusion models are powerful generative models that allow for precise control over the characteristics of the generated samples.<n>While these diffusion models trained on large datasets have achieved success, there is often a need to introduce additional controls in downstream fine-tuning processes.<n>This work presents a novel method based on reinforcement learning (RL) to add such controls using an offline dataset.
  arXiv  Detail & Related papers  (2024-06-17T22:00:26Z)
• Improving Consistency Models with Generator-Augmented Flows [16.049476783301724]
  Consistency models imitate the multi-step sampling of score-based diffusion in a single forward pass of a neural network.<n>They can be learned in two ways: consistency distillation and consistency training.<n>We propose a novel flow that transports noisy data towards their corresponding outputs derived from a consistency model.
  arXiv  Detail & Related papers  (2024-06-13T20:22:38Z)
• Adaptive Training Meets Progressive Scaling: Elevating Efficiency in Diffusion Models [52.1809084559048]
  We propose a novel two-stage divide-and-conquer training strategy termed TDC Training.<n>It groups timesteps based on task similarity and difficulty, assigning highly customized denoising models to each group, thereby enhancing the performance of diffusion models.<n>While two-stage training avoids the need to train each model separately, the total training cost is even lower than training a single unified denoising model.
  arXiv  Detail & Related papers  (2023-12-20T03:32:58Z)
• FTFT: Efficient and Robust Fine-Tuning by Transferring Training Dynamics [7.58472343957521]
  We show that training dynamics are highly transferable across model sizes and pre-training methods.<n>We propose a novel fine-tuning approach: Fine-Tuning by transFerring Training dynamics (FTFT)
  arXiv  Detail & Related papers  (2023-10-10T12:53:48Z)
• BOOT: Data-free Distillation of Denoising Diffusion Models with Bootstrapping [64.54271680071373]
  Diffusion models have demonstrated excellent potential for generating diverse images. Knowledge distillation has been recently proposed as a remedy that can reduce the number of inference steps to one or a few. We present a novel technique called BOOT, that overcomes limitations with an efficient data-free distillation algorithm.
  arXiv  Detail & Related papers  (2023-06-08T20:30:55Z)
• Diff-Instruct: A Universal Approach for Transferring Knowledge From Pre-trained Diffusion Models [77.83923746319498]
  We propose a framework called Diff-Instruct to instruct the training of arbitrary generative models. We show that Diff-Instruct results in state-of-the-art single-step diffusion-based models. Experiments on refining GAN models show that the Diff-Instruct can consistently improve the pre-trained generators of GAN models.
  arXiv  Detail & Related papers  (2023-05-29T04:22:57Z)
• Structural Pruning for Diffusion Models [65.02607075556742]
  We present Diff-Pruning, an efficient compression method tailored for learning lightweight diffusion models from pre-existing ones. Our empirical assessment, undertaken across several datasets highlights two primary benefits of our proposed method.
  arXiv  Detail & Related papers  (2023-05-18T12:38:21Z)
• FedAUX: Leveraging Unlabeled Auxiliary Data in Federated Learning [14.10627556244287]
  Federated Distillation (FD) is a popular novel algorithmic paradigm for Federated Learning. We propose FedAUX, which drastically improves performance by deriving maximum utility from the unlabeled auxiliary data. Experiments on large-scale convolutional neural networks and transformer models demonstrate, that the training performance of FedAUX exceeds SOTA FL baseline methods.
  arXiv  Detail & Related papers  (2021-02-04T09:53:53Z)

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.