根据学习难度动态调整生成路径，提升采样质量。
Difficulty-Calibrated Interpolation Paths for Conditional Flow Matching
- 用模型自适应计算每步难度，动态调整插值路径
- 在CIFAR-10上达最优FID，小样本更新时优势明显
- 兼容无分类器引导，训练开销仅增加2%
条件流匹配通过回归网络拟合预设噪声到数据的插值路径速度来训练生成模型。现有方法通常固定使用线性插值路径，未考虑数据和模型差异。我们发现条件流匹配在路径不同位置的学习难度存在系统性差异，提出难度校准流匹配：先以线性路径进行短时预训练，记录各时间步损失，再将调度策略设为该难度分布的分位数函数，使路径在最难学习处停留更久。该方法仅含一个超参数，保持原训练目标与梯度等价性，可与无分类器引导组合，训练开销约增加2%。在相同紧凑U-Net架构下，于CIFAR-10、MNIST和Fashion-MNIST上的控制实验表明，校准路径在全采样预算下取得最佳FID，且在大批次、少更新的资源受限场景中显著优于所有固定调度策略。
原文摘要 · Abstract (English)
Conditional Flow Matching trains generative models by regressing a network onto the velocity of a prescribed noise-to-data interpolation path. The interpolation schedule that shapes this path is known to affect convergence and sample quality, yet it is invariably fixed in advance, independent of both the data and the model. We show that the regression difficulty of Conditional Flow Matching varies systematically along the path, and we propose Difficulty-Calibrated Flow Matching, which derives the schedule from the model itself: a short pilot run with the linear path records the per-time loss, and the schedule is set to the quantile function of this difficulty profile, so the trajectory lingers where the velocity is hardest to learn. The method has a single hyperparameter, leaves the training objective and its gradient equivalence intact, composes with classifier-free guidance, and adds about two percent training overhead. In controlled experiments on CIFAR-10, MNIST, and Fashion-MNIST with an identical compact U-Net, the calibrated path attains the best FID on CIFAR-10 at full sampling budget and clearly outperforms all fixed schedules in the large-batch, few-update regime, precisely the setting where compute is scarcest.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。