Identifying low-energy adsorption geometries on catalytic surfaces is a practical bottleneck for computational heterogeneous catalysis: the difficulty lies not only in the cost of density functional theory (DFT) but in proposing initial placements that relax into the correct energy basins. Conditional denoising diffusion has improved success rates, yet requires $\sim$100 iterative steps per sample. Here we introduce AdsorbFlow, a deterministic generative model that learns an energy-conditioned vector field on the rigid-body configuration space of adsorbate translation and rotation via conditional flow matching. Energy information enters through classifier-free guidance conditioning -- not energy-gradient guidance -- and sampling reduces to integrating an ODE in as few as 5 steps. On OC20-Dense with full DFT single-point verification, AdsorbFlow with an EquiformerV2 backbone achieves 61.4% SR@10 and 34.1% SR@1 -- surpassing AdsorbDiff (31.8% SR@1, 41.0% SR@10) at every evaluation level and AdsorbML (47.7% SR@10) -- while using 20 times fewer generative steps and achieving the lowest anomaly rate among generative methods (6.8%). On 50 out-of-distribution systems, AdsorbFlow retains 58.0% SR@10 with a MLFF-to-DFT gap of only 4~percentage points. These results establish that deterministic transport is both faster and more accurate than stochastic denoising for adsorbate placement.

翻译：识别催化表面上的低能吸附构型是计算多相催化的实际瓶颈：难点不仅在于密度泛函理论（DFT）的计算成本，更在于提出能够弛豫至正确能量势阱的初始放置构型。条件去噪扩散方法虽已提升成功率，但每个样本仍需约100次迭代步骤。本文提出AdsorbFlow，一种确定性生成模型，它通过条件流匹配在吸附物平动与转动的刚体构型空间上学习一个能量条件向量场。能量信息通过无分类器引导条件（而非能量梯度引导）引入，采样过程简化为仅需约5步的常微分方程积分。在采用完整DFT单点验证的OC20-Dense数据集上，以EquiformerV2为骨干网络的AdsorbFlow实现了61.4%的SR@10与34.1%的SR@1——在各项评估指标上均超越AdsorbDiff（SR@1为31.8%，SR@10为41.0%）与AdsorbML（SR@10为47.7%）——同时生成步骤减少20倍，并达到生成方法中最低的异常率（6.8%）。在50个分布外体系上，AdsorbFlow仍保持58.0%的SR@10，且MLFF与DFT间的性能差距仅为4个百分点。这些结果表明，对于吸附物放置任务，确定性传输方法比随机去噪方法更快且更准确。