AlphaFlow：理解与改进MeanFlow模型

摘要

MeanFlow作为一种从零开始训练的少步生成建模框架近期崭露头角，但其成功机制尚未被完全理解。本研究表明，MeanFlow目标函数可自然解构为轨迹流匹配与轨迹一致性两个组成部分。通过梯度分析，我们发现这两项存在强烈负相关性，导致优化冲突与收敛缓慢。基于此发现，我们提出了alpha-Flow——一个将轨迹流匹配、Shortcut Model和MeanFlow统一于单一公式的广义目标函数族。通过采用从轨迹流匹配平滑过渡至MeanFlow的课程学习策略，alpha-Flow有效解耦了冲突目标并实现更优收敛性。在类条件ImageNet-1K 256×256数据集上使用标准DiT主干网络从零训练时，alpha-Flow在不同规模与设置下均持续超越MeanFlow。我们最大的alpha-Flow-XL/2+模型在使用标准DiT主干网络的条件下取得了最新顶尖成果：单步推理FID达2.58，两步推理FID达2.15。

English

MeanFlow has recently emerged as a powerful framework for few-step generative modeling trained from scratch, but its success is not yet fully understood. In this work, we show that the MeanFlow objective naturally decomposes into two parts: trajectory flow matching and trajectory consistency. Through gradient analysis, we find that these terms are strongly negatively correlated, causing optimization conflict and slow convergence. Motivated by these insights, we introduce alpha-Flow, a broad family of objectives that unifies trajectory flow matching, Shortcut Model, and MeanFlow under one formulation. By adopting a curriculum strategy that smoothly anneals from trajectory flow matching to MeanFlow, alpha-Flow disentangles the conflicting objectives, and achieves better convergence. When trained from scratch on class-conditional ImageNet-1K 256x256 with vanilla DiT backbones, alpha-Flow consistently outperforms MeanFlow across scales and settings. Our largest alpha-Flow-XL/2+ model achieves new state-of-the-art results using vanilla DiT backbones, with FID scores of 2.58 (1-NFE) and 2.15 (2-NFE).

AlphaFlow：理解与改进MeanFlow模型

AlphaFlow: Understanding and Improving MeanFlow Models

摘要

Support