Generative Pseudo-Force Fields for Molecular Generation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hessmann, Stefaan Simon Pierre, Kahouli, Khaled, Gugler, Stefan, Plainer, Michael, Noé, Frank, Müller, Klaus-Robert, Gebauer, Niklas Wolf Andreas
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911696474341376
author Hessmann, Stefaan Simon Pierre
Kahouli, Khaled
Gugler, Stefan
Plainer, Michael
Noé, Frank
Müller, Klaus-Robert
Gebauer, Niklas Wolf Andreas
author_facet Hessmann, Stefaan Simon Pierre
Kahouli, Khaled
Gugler, Stefan
Plainer, Michael
Noé, Frank
Müller, Klaus-Robert
Gebauer, Niklas Wolf Andreas
contents Generating stable molecular conformations typically forces a tradeoff between the physical realism of energy-based relaxation and the sampling efficiency of data-driven generative models. While machine learning force fields (MLFFs) can sample stable conformations by relaxing molecular geometries according to physical forces, they require costly ab-initio training data. Conversely, diffusion models (DMs) learn from equilibrium data alone but are dependent on noise schedules and time-step conditioning. In this work, we propose generative pseudo-force fields (GPFFs) to bridge these paradigms by training an MLFF on a quadratic pseudo-potential energy surface relative to reference equilibrium structures. Because no ab-initio calculations are required for the perturbed geometries, non-equilibrium training data can be generated on the fly by perturbing the equilibria with Gaussian noise. We show that GPFFs constitute a time-step-agnostic variant of variance exploding DMs: the score comes from the predicted pseudo-forces but because force magnitudes implicitly encode the noise level, no time-step conditioning is needed. Our GPFF can hence be used as a drop-in replacement in standard diffusion sampling (ancestral, Heun) but also facilitates more efficient, adaptive variants and an MLFF inspired direct denoising scheme. Our proposed sampling algorithms support arbitrary structural priors and geometric constraints. On QM9, GPFF has 100 % validity at 256 neural function evaluations (NFE) and over 50 % at just 6 NFE, outperforming diffusion baselines across all samplers. Combined with custom priors, we showcase the fast and accurate generation process of our method in a molecular editor for a drug design setting, where a molecule is generated in real time.
format Preprint
id arxiv_https___arxiv_org_abs_2605_19050
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Generative Pseudo-Force Fields for Molecular Generation
Hessmann, Stefaan Simon Pierre
Kahouli, Khaled
Gugler, Stefan
Plainer, Michael
Noé, Frank
Müller, Klaus-Robert
Gebauer, Niklas Wolf Andreas
Machine Learning
Chemical Physics
Quantitative Methods
Generating stable molecular conformations typically forces a tradeoff between the physical realism of energy-based relaxation and the sampling efficiency of data-driven generative models. While machine learning force fields (MLFFs) can sample stable conformations by relaxing molecular geometries according to physical forces, they require costly ab-initio training data. Conversely, diffusion models (DMs) learn from equilibrium data alone but are dependent on noise schedules and time-step conditioning. In this work, we propose generative pseudo-force fields (GPFFs) to bridge these paradigms by training an MLFF on a quadratic pseudo-potential energy surface relative to reference equilibrium structures. Because no ab-initio calculations are required for the perturbed geometries, non-equilibrium training data can be generated on the fly by perturbing the equilibria with Gaussian noise. We show that GPFFs constitute a time-step-agnostic variant of variance exploding DMs: the score comes from the predicted pseudo-forces but because force magnitudes implicitly encode the noise level, no time-step conditioning is needed. Our GPFF can hence be used as a drop-in replacement in standard diffusion sampling (ancestral, Heun) but also facilitates more efficient, adaptive variants and an MLFF inspired direct denoising scheme. Our proposed sampling algorithms support arbitrary structural priors and geometric constraints. On QM9, GPFF has 100 % validity at 256 neural function evaluations (NFE) and over 50 % at just 6 NFE, outperforming diffusion baselines across all samplers. Combined with custom priors, we showcase the fast and accurate generation process of our method in a molecular editor for a drug design setting, where a molecule is generated in real time.
title Generative Pseudo-Force Fields for Molecular Generation
topic Machine Learning
Chemical Physics
Quantitative Methods
url https://arxiv.org/abs/2605.19050