时间均衡平均流：弥合一步生成的尺度差距
Temporal Equilibrium MeanFlow: Bridging the Scale Gap for One-Step Generation
TEMF 通过时间均衡加权和动态边界调度器解决了 MeanFlow 在一步生成中的时间尺度不平衡问题，使一步生成达到 SOTA FID，为视觉生成任务提供了无需改变架构的稳定训练策略。
原文依据 Temporal Equilibrium MeanFlow (TEMF), which balances these competing demands through two simple yet effective components
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论MeanFlow 是一个强大的少步生成框架，可以从头开始训练，但当一步损失使用大部分训练数据时，其性能会显著下降。这源于时间尺度不平衡：来自不同生成阶段的梯度贡献不均，导致优化不稳定——表现为样本模糊和弗雷歇初始距离分数高。核心问题是两种相反力量之间的冲突：在长时间跨度上放大方差的项与在生成开始时所需的强约束，固定的采样策略无法调和这一冲突。为了解决这个问题，我们提出了时间均衡平均流（TEMF），通过两个简单而有效的组件来平衡这些竞争需求：（1）一个时间均衡加权函数，使梯度影响在所有时间尺度上均等；（2）一个动态边界调度器，随着训练进展逐渐转移训练焦点——从稳定早期步骤到细化完整轨迹。在不改变模型架构的情况下，TEMF 保留了带有无分类器引导的真正一步生成，在 ImageNet 256x256 上达到了最优的弗雷歇初始距离 2.62——在基于扩散和流的一步方法中取得了最佳结果。
英文原文摘要 1263 字符
MeanFlow is a powerful few-step generative framework that can be trained from scratch, but its performance degrades significantly when the one-step loss uses a large portion of training data. This stems from a temporal scale imbalance: gradients from different stages of generation contribute unevenly, leading to unstable optimization--evident in blurry samples and high FID scores. The core issue is a conflict between two opposing forces: terms that amplify variance over long time spans and strong constraints needed near the start of generation, which a fixed sampling strategy cannot reconcile. To resolve this, we propose Temporal Equilibrium MeanFlow (TEMF), which balances these competing demands through two simple yet effective components: (1) a temporal equilibrium weighting function that equalizes gradient influence across all time scales, and (2) a dynamic boundary scheduler that gradually shifts training focus--from stabilizing early steps to refining the full trajectory as training progresses. Without changing the model architecture, TEMF retains true one-step generation with classifier-free guidance, achieving a state-of-the-art FID of 2.62 on ImageNet 256x256--achieving the best results among diffusion- and flow-based one-step methods.