SubFlow: Sub-mode Conditioned Flow Matching for Diverse One-Step Generation

• URL: http://arxiv.org/abs/2604.12273v1
• Date: Tue, 14 Apr 2026 04:36:02 GMT
• Title: SubFlow: Sub-mode Conditioned Flow Matching for Diverse One-Step Generation
• Abstract summary: SubFlow is a flow matching framework that eliminates averaging distortion by each class into fine-grained sub-modes.<n>It integrates seamlessly into existing one-step models such as MeanFlow and Shortcut Models.<n>Experiments on ImageNet-256 demonstrate that SubFlow yields substantial gains in generation diversity (Recall) while maintaining competitive image quality (FID)
• Score: 49.024920867668754
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Flow matching has emerged as a powerful generative framework, with recent few-step methods achieving remarkable inference acceleration. However, we identify a critical yet overlooked limitation: these models suffer from severe diversity degradation, concentrating samples on dominant modes while neglecting rare but valid variations of the target distribution. We trace this degradation to averaging distortion: when trained with MSE objectives, class-conditional flows learn a frequency-weighted mean over intra-class sub-modes, causing the model to over-represent high-density modes while systematically neglecting low-density ones. To address this, we propose SubFlow, Sub-mode Conditioned Flow Matching, which eliminates averaging distortion by decomposing each class into fine-grained sub-modes via semantic clustering and conditioning the flow on sub-mode indices. Each conditioned sub-distribution is approximately unimodal, so the learned flow accurately targets individual modes with no averaging distortion, restoring full mode coverage in a single inference step. Crucially, SubFlow is entirely plug-and-play: it integrates seamlessly into existing one-step models such as MeanFlow and Shortcut Models without any architectural modifications. Extensive experiments on ImageNet-256 demonstrate that SubFlow yields substantial gains in generation diversity (Recall) while maintaining competitive image quality (FID), confirming its broad applicability across different one-step generation frameworks. Project page: https://yexionglin.github.io/subflow.

Related papers

• 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)
• IR-Flow: Bridging Discriminative and Generative Image Restoration via Rectified Flow [46.532530550015736]
  We propose IR-Flow, a novel image restoration method based on Rectified Flow.<n>We first construct multilevel data distribution flows, which expand the ability of models to learn from and adapt to various levels of degradation.<n>We show that directly establishing a linear transport flow between degraded and clean image domains not only enables fast inference but also improves adaptability to out-of-distribution degradations.
  arXiv  Detail & Related papers  (2026-04-21T16:58:14Z)
• Training-Free Refinement of Flow Matching with Divergence-based Sampling [17.850801452423074]
  Flow Divergence Sampler (FDS) is a training-free framework that refines intermediate states before each solver step.<n>FDS exploits this signal to steer states toward less ambiguous regions.<n>As a plug-and-play framework compatible with standard solvers and off-the-shelf flow backbones, FDS consistently improves fidelity across various generation tasks.
  arXiv  Detail & Related papers  (2026-04-06T12:54:58Z)
• MixFlow: Mixture-Conditioned Flow Matching for Out-of-Distribution Generalization [31.579433319908485]
  We introduce MixFlow, a conditional flow-matching framework for descriptor-controlled generation.<n>MixFlow enables smooth and extrapolation to unseen conditions, leading to substantially improved out-of-distribution generalization.<n>We empirically demonstrate its effectiveness across multiple domains, including prediction of responses to unseen perturbations in single-cell transcriptomic data and high-content microscopy-based drug screening tasks.
  arXiv  Detail & Related papers  (2026-01-16T23:13:21Z)
• Align Your Flow: Scaling Continuous-Time Flow Map Distillation [63.927438959502226]
  Flow maps connect any two noise levels in a single step and remain effective across all step counts.<n>We extensively validate our flow map models, called Align Your Flow, on challenging image generation benchmarks.<n>We show text-to-image flow map models that outperform all existing non-adversarially trained few-step samplers in text-conditioned synthesis.
  arXiv  Detail & Related papers  (2025-06-17T15:06:07Z)
• Contrastive Flow Matching [61.60002028726023]
  We introduce Contrastive Flow Matching, an extension to the flow matching objective that explicitly enforces uniqueness across all conditional flows.<n>Our approach adds a contrastive objective that maximizes dissimilarities between predicted flows from arbitrary sample pairs.<n>We find that training models with Contrastive Flow Matching (1) improves training speed by a factor of up to 9x, (2) requires up to 5x fewer de-noising steps and (3) lowers FID by up to 8.9 compared to training the same models with flow matching.
  arXiv  Detail & Related papers  (2025-06-05T17:59:58Z)
• Flowing from Words to Pixels: A Noise-Free Framework for Cross-Modality Evolution [14.57591222028278]
  We present a general and simple framework, CrossFlow, for cross-modal flow matching.<n>We show the importance of applying Variationals to the input data, and introduce a method to enable-free guidance.<n>To demonstrate the generalizability of our approach, we also show that CrossFlow is on par with or outperforms the state-of-the-art for various cross-modal / intramodal mapping tasks.
  arXiv  Detail & Related papers  (2024-12-19T18:59:56Z)
• Efficient Diversity-Preserving Diffusion Alignment via Gradient-Informed GFlowNets [65.42834731617226]
  We propose a reinforcement learning method for diffusion model finetuning, dubbed Nabla-GFlowNet.<n>We show that our proposed method achieves fast yet diversity- and prior-preserving finetuning of Stable Diffusion, a large-scale text-conditioned image diffusion model.
  arXiv  Detail & Related papers  (2024-12-10T18:59:58Z)
• AdaFlow: Imitation Learning with Variance-Adaptive Flow-Based Policies [21.024480978703288]
  We propose AdaFlow, an imitation learning framework based on flow-based generative modeling. AdaFlow represents the policy with state-conditioned ordinary differential equations (ODEs) We show that AdaFlow achieves high performance with fast inference speed.
  arXiv  Detail & Related papers  (2024-02-06T10:15:38Z)
• Guided Flows for Generative Modeling and Decision Making [55.42634941614435]
  We show that Guided Flows significantly improves the sample quality in conditional image generation and zero-shot text synthesis-to-speech. Notably, we are first to apply flow models for plan generation in the offline reinforcement learning setting ax speedup in compared to diffusion models.
  arXiv  Detail & Related papers  (2023-11-22T15:07:59Z)
• DeFlow: Learning Complex Image Degradations from Unpaired Data with Conditional Flows [145.83812019515818]
  We propose DeFlow, a method for learning image degradations from unpaired data. We model the degradation process in the latent space of a shared flow-decoder network. We validate our DeFlow formulation on the task of joint image restoration and super-resolution.
  arXiv  Detail & Related papers  (2021-01-14T18:58:01Z)

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.