One-Step Generative Modeling

Overview

One-step generative modeling aims to produce realistic samples with a single model evaluation instead of repeatedly denoising or integrating a trajectory. Common approaches distill multi-step diffusion or flow teachers, train consistency and MeanFlow models, or learn direct transport maps using distribution matching, drifting, or optimal transport. These methods are tested on image-generation benchmarks such as ImageNet and FID, as well as language, audio, video, scientific forecasting, and robotic control tasks. The central challenge is to retain the quality, diversity, and conditional accuracy of multi-step models while reducing inference cost; trajectory design, data-noise coupling, and evaluation beyond a single metric remain important concerns.

Latest papers

CardsList

156 papers13 papers in the last four weeks, down 52% on the four weeks before. 0.1% of all new papers.

  1. Manifold-Aligned Generative Transport

    Feb 23, 2026Xinyu Tian, Xiaotong ShenOne-Step Generative ModelingGenerative Modeling

  2. ChordEdit: One-Step Low-Energy Transport for Image Editing

    Feb 22, 2026Liangsi Lu, Xuhang Chen, Minzhe Guo +3Text-Guided Image EditingDiffusion-Based Image Editing

  3. Image Generation with a Sphere Encoder

    Feb 16, 2026Kaiyu Yue, Menglin Jia, Ji Hou +1Image GenerationOne-Step Generative Modeling

  4. Dual-End Consistency Model

    Feb 11, 2026Linwei Dong, Ruoyu Guo, Ge Bai +3One-Step Generative ModelingConsistency Distillation

  5. SSDD: Single-Step Diffusion Decoder for Efficient Image Tokenization

    Oct 6, 2025Théophane Vallaeys, Jakob Verbeek, Matthieu CordImage TokenizationImage Reconstruction