---
title: "ROMS-IMLE：一种极简的竞争性单步生成建模方法"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2607.19332v1"
permalink: "https://feed.astralor.com/items/itm_5b9493515a999bafab0ad638"
published: "2026-07-21T17:51:38.000Z"
score: 79
channel: "ai"
tags: ["ROMS-IMLE","单步生成","卷积网络","极简生成模型","隐式最大似然估计"]
---

# ROMS-IMLE：一种极简的竞争性单步生成建模方法

## AI 点评

> 这篇论文直击生成模型领域近年来的“堆叠复杂度”风气，用最简单的IMLE+CNN实现单步竞争性能，非常值得关注。对正在寻找高效部署方案的工程师或想挑战主流叙事的理论研究者来说，这是不容错过的灵感来源。

## 速览

本文挑战了生成模型中渐进式噪声变换的必要性，提出ROMS-IMLE这一极简框架。该方法仅使用隐式最大似然估计（IMLE）作为训练目标，搭配中等规模的卷积网络，避免了迭代去噪、变换器架构和复杂推理。在ImageNet 256上以单步生成达到FID 2.56，同时保持良好精度和召回率，证明简洁设计可以取得竞争力的生成质量与速度。

## 关键点

- 提出ROMS-IMLE，一种完全避免迭代去噪的单步生成模型。
- 仅用IMLE训练目标和中等规模卷积网络，不依赖变换器或变分推理。
- 在ImageNet 256上以单步生成达到FID 2.56，精度和召回率良好。
- 挑战了“多步噪声变换是高性能生成模型关键”的普遍观点。

## 全文

Generative models have undergone many generations of evolution, from VAEs/GANs to diffusion/flow matching. Along the way, the underlying techniques have become more complicated and various beliefs about what drives strong empirical performance have taken hold. Due to the success of diffusion models and flow matching, one of the more common beliefs is the importance of transforming the noise distribution to the data distribution gradually through many small transformations. We ask whether this is truly necessary, and take a minimalist approach to designing a competitive generative model. We start with the bare-bones essentials, namely just a training objective and a model. We purposefully make both simple. For the training objective, we choose Implicit Maximum Likelihood Estimation (IMLE), and eschew more complicated alternatives such as variational inference, adversarial training and numerical integration. For the model, we eschew transformers and instead choose a moderately sized convolutional network. Then we judiciously added elements that are truly essential, which surprisingly do not include iterative denoising. The result is a single-step parameter-efficient generative model that produces high quality samples at fast speed: it achieves an FID of 2.56 on ImageNet 256 and simultaneously attains good precision and recall.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_5b9493515a999bafab0ad638