AdsorbFlow: energy-conditioned flow matching enables fast and realistic adsorbate placement

TL;DR

AdsorbFlow is a fast, energy-conditioned flow model that efficiently predicts low-energy adsorbate configurations on catalytic surfaces, outperforming previous methods in accuracy and speed.

Contribution

It introduces a deterministic flow-based model with energy conditioning for adsorbate placement, reducing sampling steps and improving accuracy over existing stochastic methods.

Findings

Achieves 61.4% SR@10 and 34.1% SR@1 on OC20-Dense

Uses 20 times fewer steps than previous models

Maintains high accuracy on out-of-distribution systems

Abstract

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.