Coarse-Grained Boltzmann Generators
Not on the map. Why?
Abstract (arXiv)
Sampling equilibrium molecular configurations from the Boltzmann distribution is a longstanding challenge. Boltzmann Generators (BGs) address this by combining exact-likelihood generative models with importance sampling, but practical scalability is limited. Meanwhile, coarse-grained surrogates enable the modeling of larger systems by reducing effective dimensionality, yet often lack a reweighting procedure required to ensure asymptotically correct statistics. In this work, we propose Coarse-Grained Boltzmann Generators (CG-BGs), a framework for reduced-order generative modeling with importance sampling in coarse-grained coordinate space. CG-BGs generate samples using a flow-based model and reweight them using a learned potential of mean force (PMF). We show that the PMF can be learned from rapidly converged trajectories via enhanced sampling force matching. Experiments demonstrate that CG-BGs capture solvent-mediated interactions in highly reduced representations while substantially reducing computational cost relative to atomistic BGs, providing a practical route toward equilibrium sampling of larger molecular systems.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 56 of its 130 references that are in the map. First posted on arXiv 11 Feb 2026.
Builds on
56 of 130 references.
References · 56
- 2022Flow Matching for Generative Modelingcited by 5,426
- 2018Neural Ordinary Differential Equationscited by 3,733
- 2015Variational Inference with Normalizing Flowscited by 2,161
- 2014NICE: Non-linear Independent Components Estimationcited by 1,052
- 2023Stochastic Interpolants: A Unifying Framework for Flows and Diffusionscited by 897
- 2023Improving and generalizing flow-based generative models with minibatch optimal transportcited by 835
- 2021E(3)-Equivariant Graph Neural Networks for Data-Efficient and Accurate Interatomic Potentialscited by 701
- 2020Masked Label Prediction: Unified Message Passing Model for Semi-Supervised Classificationcited by 500
- 2022MACE: Higher Order Equivariant Message Passing Neural Networks for Fast and Accurate Force Fieldscited by 467
- 2022On Neural Differential Equationscited by 264
- 2020Equivariant Flows: Exact Likelihood Generative Learning for Symmetric Densitiescited by 248
- 2019Rapid Convergence of the Unadjusted Langevin Algorithm: Isoperimetry Sufficescited by 224
38 more
- 2020Machine Learning Force Fieldscited by 204
- 2019Flow-based generative models for Markov chain Monte Carlo in lattice field theorycited by 147
- 2024Iterated Denoising Energy Matching for Sampling from Boltzmann Densitiescited by 113
- 2024AlphaFold Meets Flow Matching for Generating Protein Ensemblescited by 105
- 2025UMA: A Family of Universal Models for Atomscited by 99
- 2024Normalizing Flows are Capable Generative Modelscited by 89
- 2025Adjoint Sampling: Highly Scalable Diffusion Samplers via Adjoint Matchingcited by 78
- 2023Two for One: Diffusion Models and Force Fields for Coarse-Grained Molecular Dynamicscited by 72
- 2018Machine Learning of coarse-grained Molecular Dynamics Force Fieldscited by 68
- 2020Targeted free energy estimation via learned mappingscited by 66
- 2023Timewarp: Transferable Acceleration of Molecular Dynamics by Learning Time-Coarsened Dynamicscited by 62
- 2023OpenMM 8: Molecular Dynamics Simulation with Machine Learning Potentialscited by 44
- 2024Transferable Boltzmann Generatorscited by 43
- 2022Machine Learning Coarse-Grained Potentials of Protein Thermodynamicscited by 37
- 2022Flow-matching -- efficient coarse-graining of molecular dynamics without forcescited by 36
- 2025Scalable Equilibrium Sampling with Sequential Boltzmann Generatorscited by 36
- 2021Learning neural network potentials from experimental data via Differentiable Trajectory Reweightingcited by 26
- 2025No Trick, No Treat: Pursuits and Challenges Towards Simulation-free Training of Neural Samplerscited by 25
- 2017Molecular enhanced sampling with autoencoders: On-the-fly collective variable discovery and accelerated free energy landscape explorationcited by 24
- 2025Consistent Sampling and Simulation: Molecular Dynamics with Energy-Based Diffusion Modelscited by 23
- 2023Navigating protein landscapes with a machine-learned transferable coarse-grained modelcited by 22
- 2022Generative Coarse-Graining of Molecular Conformationscited by 21
- 2025Action-Minimization Meets Generative Modeling: Efficient Transition Path Sampling with the Onsager-Machlup Functionalcited by 18
- 2025Tilt Matching for Scalable Sampling and Fine-Tuningcited by 17
- 2021Machine Learning Implicit Solvation for Molecular Dynamicscited by 16
- 2023Uncertainty-biased molecular dynamics for learning uniformly accurate interatomic potentialscited by 16
- 2025FALCON: Few-step Accurate Likelihoods for Continuous Flowscited by 12
- 2025Amortized Sampling with Transferable Normalizing Flowscited by 11
- 2025Scalable Boltzmann Generators for equilibrium sampling of large-scale materialscited by 11
- 2025Enhancing Diffusion-Based Sampling with Molecular Collective Variablescited by 9
- 2025Transferable Generative Models Bridge Femtosecond to Nanosecond Time-Step Molecular Dynamicscited by 8
- 2025Learning Boltzmann Generators via Constrained Mass Transportcited by 8
- 2025chemtrain-deploy: A parallel and scalable framework for machine learning potentials in million-atom MD simulationscited by 6
- 2025Accelerating Protein Molecular Dynamics Simulation with DeepJumpcited by 6
- 2024Conditional Normalizing Flows for Active Learning of Coarse-Grained Molecular Representationscited by 5
- 2025HollowFlow: Efficient Sample Likelihood Evaluation using Hollow Message Passingcited by 5
- 2026A Diffusive Classification Loss for Learning Energy-based Generative Modelscited by 5
- 2024AMARO: All Heavy-Atom Transferable Neural Network Potentials of Protein Thermodynamicscited by 3
50 most cited of 56 All 56 (JSON)
Built on by
Not cited yet.