OMatG-flash: An All-Atom Flow Map with Reinforce Adjoint Matching for Scalable Materials Discovery
cs.LG
Submitted: 2026-09-22
Updated: 2026-09-22
Comments: 27 pages, 5 figures
Code: https://github.com/FERMat-ML/OMatG
License: http://creativecommons.org/licenses/by/4.0/
The gist: The discovery of novel inorganic materials drives technological breakthroughs in critical fields such as computing and energy storage.
Terminology
Abstract
The discovery of novel inorganic materials drives technological breakthroughs in critical fields such as computing and energy storage. Generative AI has promised to accelerate the materials discovery pipeline, but state-of-the-art flow and diffusion models remain bottlenecked by the cost of proposing candidate materials. To address this, we introduce OMatG-flash, an all-atom flow map for inorganic crystal structure prediction (CSP) and de novo generation (DNG). OMatG-flash is a Pareto-optimal inference engine for materials, sampling candidate materials with an order of magnitude fewer inference steps and less wall-clock time than existing flow and diffusion models while demonstrating benchmark performance on par with the state-of-the-art. To enable post-training fine-tuning we apply Reinforce Adjoint Matching to flow maps, further improving match rates and RMSE on the unconditional CSP task. OMatG-flash showcases the potential of flow maps to accelerate generation of high-quality candidate inorganic materials and demonstrates a step forward in sample throughput necessary for data-hungry materials discovery workflows.
Sources
- Ab initio Random Structure Searching
- A foundation model for atomistic materials chemistry
- UMA: A Family of Universal Models for Atoms
- Crystal Diffusion Variational Autoencoder for Periodic Material Generation
- Crystal Structure Prediction by Joint Equivariant Diffusion
- FlowMM: Generating Materials with Riemannian Flow Matching
- MatterGen: a generative model for inorganic materials design
- Open Materials Generation with Stochastic Interpolants
- Stochastic Interpolants: A Unifying Framework for Flows and Diffusions
- Deep Unsupervised Learning using Nonequilibrium Thermodynamics
- Score-Based Generative Modeling through Stochastic Differential Equations
- Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow
- Flow Matching for Generative Modeling
- Riemannian MeanFlow
- Flow map matching with stochastic interpolants: A mathematical framework for consistency models
- How to build a consistency model: Learning flow maps via self-distillation
- Self-conditioned Flow Map Language Models via Fixed-point Flows
- Few-step Cofolding with All-Atom Flow Maps
- Flow Map Language Models: One-step Language Modeling via Continuous Denoising
- Learning Hamiltonian Flow Maps: Mean Flow Consistency for Large-Timestep Molecular Dynamics
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks