mlsanityData to 14 Oct 2026

Transferable Boltzmann Generators

arXiv 2406.14426 ↗First posted 20 Jun 2024stat.ML cs.LG physics.chem-phcited by 46

Not on the map. Why?

Abstract (arXiv)

The generation of equilibrium samples of molecular systems has been a long-standing problem in statistical physics. Boltzmann Generators are a generative machine learning method that addresses this issue by learning a transformation via a normalizing flow from a simple prior distribution to the target Boltzmann distribution of interest. Recently, flow matching has been employed to train Boltzmann Generators for small molecular systems in Cartesian coordinates. We extend this work and propose a first framework for Boltzmann Generators that are transferable across chemical space, such that they predict zero-shot Boltzmann distributions for test molecules without being retrained for these systems. These transferable Boltzmann Generators allow approximate sampling from the target distribution of unseen systems, as well as efficient reweighting to the target Boltzmann distribution. The transferability of the proposed framework is evaluated on dipeptides, where we show that it generalizes efficiently to unseen systems. Furthermore, we demonstrate that our proposed architecture enhances the efficiency of Boltzmann Generators trained on single molecular systems.

Key facts. Cited by 46 papers in the map (data through 14 Oct 2026). Builds on 41 of its 72 references that are in the map. First posted on arXiv 20 Jun 2024.

Builds on

41 of 72 references.

References · 41

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  2. 2022Flow Matching for Generative Modelingcited by 5,702
  3. 2018Neural Ordinary Differential Equationscited by 3,779
  4. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,700
  5. 2015Variational Inference with Normalizing Flowscited by 2,170
  6. 2019Normalizing Flows for Probabilistic Modeling and Inferencecited by 1,323
  7. 2014NICE: Non-linear Independent Components Estimationcited by 1,058
  8. 2022Building Normalizing Flows with Stochastic Interpolantscited by 995
  9. 2021E(n) Equivariant Graph Neural Networkscited by 965
  10. 2022Equivariant Diffusion for Molecule Generation in 3Dcited by 677
  11. 2022GeoDiff: a Geometric Diffusion Model for Molecular Conformation Generationcited by 516
  12. 2021Equivariant message passing for the prediction of tensorial properties and molecular spectracited by 441
29 more
  1. 2021GemNet: Universal Directional Graph Neural Networks for Moleculescited by 343
  2. 2020Learning from Protein Structure with Geometric Vector Perceptronscited by 313
  3. 2022Equiformer: Equivariant Graph Attention Transformer for 3D Atomistic Graphscited by 264
  4. 2022Torsional Diffusion for Molecular Conformer Generationcited by 263
  5. 2020Equivariant Flows: Exact Likelihood Generative Learning for Symmetric Densitiescited by 250
  6. 2019Symmetry-adapted generation of 3d point sets for the targeted discovery of moleculescited by 172
  7. 2021E(n) Equivariant Normalizing Flowscited by 165
  8. 2020Stochastic Normalizing Flowscited by 157
  9. 2023Equivariant flow matchingcited by 135
  10. 2022Flow Annealed Importance Sampling Bootstrapcited by 127
  11. 2024AlphaFold Meets Flow Matching for Generating Protein Ensemblescited by 110
  12. 2020Targeted free energy estimation via learned mappingscited by 67
  13. 2023Timewarp: Transferable Acceleration of Molecular Dynamics by Learning Time-Coarsened Dynamicscited by 66
  14. 2023EigenFold: Generative Protein Structure Prediction with Diffusion Modelscited by 63
  15. 2023Equivariant Flow Matching with Hybrid Probability Transportcited by 60
  16. 2021Smooth Normalizing Flowscited by 53
  17. 2023A new perspective on building efficient and expressive 3D equivariant graph neural networkscited by 47
  18. 2024Protein Conformation Generation via Force-Guided SE(3) Diffusion Modelscited by 45
  19. 2019Equivariant Hamiltonian Flowscited by 39
  20. 2023SE(3) Equivariant Augmented Coupling Flowscited by 37
  21. 2022Flow-matching -- efficient coarse-graining of molecular dynamics without forcescited by 36
  22. 2023Harmonic Self-Conditioned Flow Matching for Multi-Ligand Docking and Binding Site Designcited by 30
  23. 2023Rigid Body Flows for Sampling Molecular Crystal Structurescited by 27
  24. 2023Free-form Flows: Make Any Architecture a Normalizing Flowcited by 26
  25. 2023Navigating protein landscapes with a machine-learned transferable coarse-grained modelcited by 23
  26. 2024Efficient mapping of phase diagrams with conditional Boltzmann Generatorscited by 18
  27. 2024Scalable Normalizing Flows Enable Boltzmann Generators for Macromoleculescited by 10
  28. 2020Computing Absolute Free Energy with Deep Generative Modelscited by 7
  29. 2023Von Mises Mixture Distributions for Molecular Conformation Generationcited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 5; 2025: 26; 2026: 15.

46 papers.

Sort:

By area:

  1. 2025Scalable Equilibrium Sampling with Sequential Boltzmann Generatorscited by 38
  2. 2025Progressive Inference-Time Annealing of Diffusion Models for Sampling from Boltzmann Densitiescited by 26
  3. 2025Consistent Sampling and Simulation: Molecular Dynamics with Energy-Based Diffusion Modelscited by 23
  4. 2025Action-Minimization Meets Generative Modeling: Efficient Transition Path Sampling with the Onsager-Machlup Functionalcited by 20
  5. 2025FEAT: Free energy Estimators with Adaptive Transportcited by 16
  6. 2025Temperature-Annealed Boltzmann Generatorscited by 15
  7. 2025FALCON: Few-step Accurate Likelihoods for Continuous Flowscited by 13
  8. 2025FlashMD: long-stride, universal prediction of molecular dynamicscited by 12
  9. 2025Amortized Sampling with Transferable Normalizing Flowscited by 12
  10. 2024Harmonic Path Integral Diffusioncited by 11
  11. 2025Scalable Boltzmann Generators for equilibrium sampling of large-scale materialscited by 11
  12. 2025Transferable Generative Models Bridge Femtosecond to Nanosecond Time-Step Molecular Dynamicscited by 11
34 more
  1. 2025On scalable and efficient training of diffusion samplerscited by 10
  2. 2025Learning Boltzmann Generators via Constrained Mass Transportcited by 9
  3. 2025Scalable Autoregressive 3D Molecule Generationcited by 8
  4. 2025UniSim: A Unified Simulator for Time-Coarsened Dynamics of Biomoleculescited by 7
  5. 2025BoltzNCE: Learning Likelihoods for Boltzmann Generation with Stochastic Interpolants and Noise Contrastive Estimationcited by 7
  6. 2025Energy-Weighted Flow Matching: Unlocking Continuous Normalizing Flows for Efficient and Scalable Boltzmann Samplingcited by 7
  7. 2026Learning Hamiltonian Flow Maps: Mean Flow Consistency for Large-Timestep Molecular Dynamicscited by 7
  8. 2024Force-Guided Bridge Matching for Full-Atom Time-Coarsened Dynamics of Peptidescited by 6
  9. 2025MarS-FM: Generative Modeling of Molecular Dynamics via Markov State Modelscited by 6
  10. 2024On the design space between molecular mechanics and machine learning force fieldscited by 4
  11. 2024JAMUN: Bridging Smoothed Molecular Dynamics and Score-Based Learning for Conformational Ensemblescited by 4
  12. 2026Protein Language Model Embeddings Improve Generalization of Implicit Transfer Operatorscited by 4
  13. 2025Path Gradients after Flow Matchingcited by 3
  14. 2025Beyond Ensembles: Simulating All-Atom Protein Dynamics in a Learned Latent Spacecited by 3
  15. 2025Enhanced Sampling for Efficient Learning of Coarse-Grained Machine Learning Potentialscited by 3
  16. 2026Efficient Training of Boltzmann Generators Using Off-Policy Log-Dispersion Regularizationcited by 3
  17. 2026Unified Biomolecular Trajectory Generation via Pretrained Variational Bridgecited by 2
  18. 2026Boltzmann-Expected Molecular Design with Decoupled Annealing Flowscited by 2
  19. 2025AI-based Methods for Simulating, Sampling, and Predicting Protein Ensemblescited by 1
  20. 2025Adaptive Path Integral Diffusion: AdaPIDcited by 1
  21. 2026Boltzmann Generators for Condensed Matter via Riemannian Flow Matchingcited by 1
  22. 2026Learning Structure, Energy, and Dynamics: A Survey of Artificial Intelligence for Protein Dynamicscited by 1
  23. 2026Autoregressive Boltzmann Generatorscited by 1
  24. 2024Efficient Generation of Molecular Clusters with Dual-Scale Equivariant Flow Matchingcited by 0
  25. 2025Operator Forces For Coarse-Grained Molecular Dynamicscited by 0
  26. 2025Latent Thermodynamic Flows: Unified Representation Learning and Generative Modeling of Temperature-Dependent Behaviors from Limited Datacited by 0
  27. 2025Torsional-GFN: a conditional conformation generator for small moleculescited by 0
  28. 2026Coarse-Grained Boltzmann Generatorscited by 0
  29. 2026CARD: Coarse-to-fine Autoregressive Modeling with Radix-based Decomposition for Transferable Free Energy Estimationcited by 0
  30. 2026Mode Coverage in Normalizing Flow Boltzmann Generators via Log-Ratio Variationcited by 0
  31. 2026Neural Transport Nested Samplingcited by 0
  32. 2026Langevin Flow Maps: Efficient Molecular Dynamics and Transition Path Samplingcited by 0
  33. 2026Looking Under the Streetlight: Evaluation in Generative Molecular Dynamicscited by 0
  34. 2026Amortised adaptive importance samplingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Efficient Regression-Based Training of Normalizing Flows for Boltzmann Generators
  2. 2025Boltzmann generators for amorphous particle systems
  3. 2026Generating Physically Consistent Molecules with Energy-Based Models
  4. 2026Diffusion-based Annealed Boltzmann Generators : benefits, pitfalls and hopes
  5. 2026FUND: Density Flow for Sampling Unnormalised Distributions
  6. 2026Few-Step Boltzmann Generators via Scalable Likelihood Flow Maps
  7. 2026AquaGen: Scaling generative models to molecular dynamics precision on thousands of atoms
  8. 2024Efficient and Unbiased Sampling of Boltzmann Distributions via Consistency Models