这篇论文发现伪随机数的选择会影响扩散模型的生成质量，不是随便什么随机源都行，看看它是怎么测的。
扩散模型在有限精度硬件上使用的随机性由伪随机规则产生，轨道结构可能成为可学习输入。研究用小型多层感知机预测轨道下一值，并用扩散探针将真实图像替换为随机张量。在MNIST和CIFAR-10上，不同伪随机源产生明显不同的扩散损失和生成质量。归一化后，探针损失与真实数据扩散损失近似遵循经验幂律，两个数据集指数不同。
Pseudorandom Streams within Diffusion Models Act as Learnable Inputs That Affect Generation Quality
Diffusion models rely on stochastic inputs, yet on finite-precision hardware, the "randomness" they consume is realized as deterministic numerical orbits generated by pseudorandom rules. Accessible orbit structure can become a learnable input and affect both training and generation because the realized loss and its gradient depend on the concrete pseudorandom values consumed at each optimization step. A small multilayer perceptron predicts the next value of an orbit from its recent history, measuring general sequence predictability. A diffusion probe replaces real images with online random tensors while preserving the diffusion architecture and training objective, measuring whether the target system can exploit orbit structure. After controlling marginal statistics and screening out clear dynamical and finite-precision failures, the remaining orbits still produce markedly different diffusion losses and generation quality on MNIST and CIFAR-10. Both measures show strong rank correlations with macroscopic generation degradation, although their local rankings differ. After normalization by the IID baseline, the probe loss and the real-data diffusion loss approximately follow an empirical power law, with different exponents on the two datasets. These results suggest that a pseudorandom source is not only a distributional choice, but also a model-dependent structured input.