做流体模拟或室内环境优化的团队终于有了一个又快又准的替代方案——Drifting Models 比扩散模型快两个数量级，精度却不输，值得在实时 CFD 场景中直接试试。
计算流体动力学（CFD）虽能高保真模拟室内环境流场，但计算成本高，限制了快速探索。为解决此问题，生成式替代模型比确定性网络能更好建模分布，但迭代采样速度慢。本文首次将生成式漂移框架（Drifting Models）应用于流体力学，提出条件架构在VAE潜在空间中进行漂移，并使用标签感知掩码对齐生成样本与边界条件。该标签条件模型在精度和流一致性上匹配迭代扩散模型，但运行速度快两个数量级。此外，空间条件变体为泛化到未见几何体铺平了道路。条件漂移成为扩散模型的高效替代方案，解锁了推理速度关键的实时CFD替代模型。
Drifting Models for Surrogate Flow Modeling
While Computational Fluid Dynamics (CFD) provides high-fidelity flow fields for optimizing indoor environments, its computational cost limits rapid exploration. To solve this problem generative surrogates offer better distribution modeling than deterministic networks, but iterative sampling is slow. To enable high-quality, single-pass generation, we adapt the novel generative drifting framework to fluid mechanics. We introduce a conditional architecture that performs drifting in a learned VAE latent space and uses label-aware masking to align generated samples with their boundary conditions. Our label-conditioned model matches iterative diffusion in accuracy and flow consistency while running two orders of magnitude faster. Additionally, we propose a spatial-conditioning variant that establishes a promising path towards generalization to unseen geometries. Ultimately, conditional drifting serves as a highly efficient alternative to diffusion based approaches, unlocking real-time CFD surrogates where inference speed is critical.