AI Paper Atlas

Research map / Probabilistic and scientific modeling / Molecules and proteins

Drift-React: One-step Generation of Reaction Pathways via SE(3) Drifting Fields

Rémi Schlama, Philippe Schwaller

NeurIPS 2026 · Probabilistic and scientific modeling › Molecules and proteins · approach: Flow matching generative modeling · 3 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes Drift-React, a one-step generative model for reaction pathways and transition states built on SE(3)-equivariant drifting fields, rather than slow iterative diffusion-style inference.

Problem

Computing minimum energy pathways and transition states with electronic-structure methods needs thousands of costly force evaluations, and existing generative TS models require slow iterative inference and predict only isolated saddle points rather than full pathways.

Approach

Generates entire reaction pathways in one step by learning SE(3)-equivariant drifting fields, instead of iterative denoising, so that the output covers the full MEP and not just a single saddle point.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use Drift-React instead of geodesic interpolationReaction pathway generation · Halo8TS-RMSD (A): 0.316 -> 0.107Improved
use Drift-React instead of retrained NeuralNEBReaction pathway generation · Halo8TS-RMSD (A): 0.538 -> 0.107Improved
use Drift-React instead of geodesic interpolationReaction pathway generation · Halo8Activation barrier MAE (eV): 1.247 -> 0.914Improved
use Drift-React instead of linear interpolationReaction pathway generation · Transition1xPer-image energy MAE (eV): ~0.92 -> 3.214Hurt
use Drift-React instead of linear interpolationReaction pathway generation · Transition1xActivation barrier MAE (eV): 1.881 -> 1.631Improved
train full pathway (F=10) instead of TS-only (F=3) (ablation)Drift-React · Transition1x TS-RMSDTS-RMSD (A): 0.168 -> 0.151Improved
use Drift-React TS-only instead of ReactOTDrift-React F=3 · Transition1x TS-onlyTS-RMSD (A): 0.103 -> 0.168Hurt
initialize TS optimization from Drift-React pathway instead of linear midpointDrift-React · Halo8 TS refinementMedian optimization cycles: 16 -> 10Improved
initialize TS optimization from Drift-React pathway instead of linear midpointDrift-React · Halo8 TS refinementMean absolute barrier error (eV): 0.143 -> 0.501Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy