RMFlow: Refined Mean Flow by a Noise-Injection Step for Multimodal Generation

2026-01-31 · Yuhao Huang, Shih-Hsin Wang, Andrea L. Bertozzi, Bao Wang arxiv

Mean flow (MeanFlow) enables efficient, high-fidelity image generation, yet its single-function evaluation (1-NFE) generation often cannot yield compelling results. We address this issue by introducing RMFlow, an efficient multimodal generative model that integrates a coarse 1-NFE MeanFlow transport with a subsequent tailored noise-injection refinement step. RMFlow approximates the average velocity of the flow path using a neural network trained with a new loss function that balances minimizing the Wasserstein distance between probability paths and maximizing sample likelihood. RMFlow achieves near state-of-the-art results on text-to-image, context-to-molecule, and time-series generation using only 1-NFE, at a computational cost comparable to the baseline MeanFlows.

📄 PDF Abstract BibTeX arXiv:2602.00849

Code (0)

등록된 구현이 없습니다.

Tasks

multimodal generation Image Generation

ARMFlow: AutoRegressive MeanFlow for Online 3D Human Reaction Generation

2025-12-18 · Zichen Geng, Zeeshan Hayder, Wei Liu, Hesheng Wang 외 arxiv

3D human reaction generation faces three main challenges:(1) high motion fidelity, (2) real-time inference, and (3) autoregressive adaptability for online scenarios. Existing methods fail to meet all three simultaneously…

What to Format and How: A Benchmark and Workflow Approach for Document Formatting

2026-06-01 · Shihao Rao, Liang Li, Jiapeng Liu, Tong Lin 외 arxiv

Recent advances in large language models (LLMs) have opened up new possibilities for automated document formatting. However, real-world formatting often requires identifying targets based on document content. This conten…

normflows: A PyTorch Package for Normalizing Flows

2023-01-26 · Vincent Stimper, David Liu, Andrew Campbell, Vincent Berenz 외

Normalizing flows model probability distributions through an expressive tractable density. They transform a simple base distribution, such as a Gaussian, through a sequence of invertible functions, which are referred to …

Image Generation Variational Inference

Learning Unbiased Permutations via Flow Matching

2026-05-16 · Yimeng Min, Carla P. Gomes arxiv

Learning permutations is fundamental to sorting, ranking, and matching, but existing differentiable methods based on entropy-regularized Sinkhorn produce a single softened solution and collapse under ambiguity. We presen…

Maximum Mean Discrepancy Gradient Flow

2019-06-11 · NeurIPS 2019 12 · Michael Arbel, Anna Korba, Adil Salim, Arthur Gretton

We construct a Wasserstein gradient flow of the maximum mean discrepancy (MMD) and study its convergence properties. The MMD is an integral probability metric defined for a reproducing kernel Hilbert space (RKHS), and se…