mlsanityData to 14 Oct 2026

Geometric Latent Diffusion Models for 3D Molecule Generation

arXiv 2305.01140 ↗First posted 2 May 2023cs.LG q-bio.QMcited by 186

On the map: Diffusion models → Flow matching, time series and science

Abstract (arXiv)

Generative models, especially diffusion models (DMs), have achieved promising results for generating feature-rich geometries and advancing foundational science problems such as molecule design. Inspired by the recent huge success of Stable (latent) Diffusion models, we propose a novel and principled method for 3D molecule generation named Geometric Latent Diffusion Models (GeoLDM). GeoLDM is the first latent DM model for the molecular geometry domain, composed of autoencoders encoding structures into continuous latent codes and DMs operating in the latent space. Our key innovation is that for modeling the 3D molecular geometries, we capture its critical roto-translational equivariance constraints by building a point-structured latent space with both invariant scalars and equivariant tensors. Extensive experiments demonstrate that GeoLDM can consistently achieve better performance on multiple molecule generation benchmarks, with up to 7% improvement for the valid percentage of large biomolecules. Results also demonstrate GeoLDM's higher capacity for controllable generation thanks to the latent modeling. Code is provided at urlhttps://github.com/MinkaiXu/GeoLDM.

Key facts. Cited by 186 papers in the map (data through 14 Oct 2026). Placed in Flow matching, time series and science, one of 14 directions in Diffusion models. Builds on 49 of its 62 references that are in the map. First posted on arXiv 2 May 2023.

Builds on

49 of 62 references.

Closest ancestors · 5

Same direction, newest first

  1. 2022Diffusion probabilistic modeling of protein backbones in 3D for the motif-scaffolding problem8 Jun
  2. 2022Protein Structure and Sequence Generation with Equivariant Denoising Diffusion Probabilistic Models26 May
  3. 2022Equivariant Diffusion for Molecule Generation in 3D31 Mar
  4. 2022GeoDiff: a Geometric Diffusion Model for Molecular Conformation Generation6 Mar
  5. 2022Score-based Generative Modeling of Graphs via the System of Stochastic Differential Equations5 Feb

Other references · 44

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  4. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  5. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  6. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,585
  7. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,101
  8. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,761
  9. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,253
  10. 2021SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equationscited by 1,937
  11. 2019Generating Diverse High-Fidelity Images with VQ-VAE-2cited by 1,387
  12. 2020DiffWave: A Versatile Diffusion Model for Audio Synthesiscited by 1,354
32 more
  1. 2022Diffusion-LM Improves Controllable Text Generationcited by 1,027
  2. 2021E(n) Equivariant Graph Neural Networkscited by 965
  3. 2016Pixel Recurrent Neural Networkscited by 816
  4. 2018Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point cloudscited by 746
  5. 2021E(3)-Equivariant Graph Neural Networks for Data-Efficient and Accurate Interatomic Potentialscited by 708
  6. 2021Vector-quantized Image Modeling with Improved VQGANcited by 658
  7. 2018Junction Tree Variational Autoencoder for Molecular Graph Generationcited by 652
  8. 2021Score-based Generative Modeling in Latent Spacecited by 636
  9. 2020SE(3)-Transformers: 3D Roto-Translation Equivariant Attention Networkscited by 607
  10. 2017SchNet: A continuous-filter convolutional neural network for modeling quantum interactionscited by 571
  11. 2022LION: Latent Point Diffusion Models for 3D Shape Generationcited by 553
  12. 20183D Steerable CNNs: Learning Rotationally Equivariant Features in Volumetric Datacited by 354
  13. 2020Learning from Protein Structure with Geometric Vector Perceptronscited by 313
  14. 2020GraphAF: a Flow-based Autoregressive Model for Molecular Graph Generationcited by 305
  15. 2019Cormorant: Covariant Molecular Neural Networkscited by 263
  16. 2019Diagnosing and Enhancing VAE Modelscited by 193
  17. 2018Constrained Graph Variational Autoencoders for Molecule Designcited by 185
  18. 2020MoFlow: An Invertible Flow Model for Generating Molecular Graphscited by 185
  19. 2022Pocket2Mol: Efficient Molecular Sampling Based on 3D Protein Pocketscited by 183
  20. 2019Symmetry-adapted generation of 3d point sets for the targeted discovery of moleculescited by 172
  21. 2019From Variational to Deterministic Autoencoderscited by 133
  22. 2022Diffusion-based Molecule Generation with Informative Prior Bridgescited by 106
  23. 2021D2C: Diffusion-Denoising Models for Few-shot Conditional Generationcited by 96
  24. 2021Inverse design of 3d molecular structures with conditional generative neural networkscited by 93
  25. 2019FlowSeq: Non-Autoregressive Conditional Sequence Generation with Generative Flowcited by 89
  26. 2020ATOM3D: Tasks On Molecules in Three Dimensionscited by 74
  27. 2020A Contrastive Learning Approach for Training Variational Autoencoder Priorscited by 66
  28. 2022DiffBP: Generative Diffusion of 3D Molecules for Target Protein Bindingcited by 58
  29. 2022Unsupervised Learning of Group Invariant and Equivariant Representationscited by 39
  30. 2021Learning to design drug-like molecules in three-dimensional space using deep generative modelscited by 37
  31. 2020Generating 3D Molecular Structures Conditional on a Receptor Binding Site with Deep Generative Modelscited by 33
  32. 2021Auto-Encoding Molecular Conformationscited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 11; 2024: 68; 2025: 66; 2026: 41.

186 papers.

Sort:

By area:

  1. 2024Derivative-Free Guidance in Continuous and Discrete Diffusion Models with Soft Value-Based Decodingcited by 136
  2. 2024TFG: Unified Training-Free Guidance for Diffusion Modelscited by 107
  3. 2024Discrete-state Continuous-time Diffusion for Graph Generationcited by 76
  4. 2025All-atom Diffusion Transformers: Unified generative modelling of molecules and materialscited by 75
  5. 2023Equivariant Flow Matching with Hybrid Probability Transportcited by 60
  6. 2024Minimax Optimality of Score-based Diffusion Models: Beyond the Density Lower Bound Assumptionscited by 47
  7. 2024Graph Diffusion Transformers for Multi-Conditional Molecular Generationcited by 45
  8. 2024Efficient Video Diffusion Models via Content-Frame Motion-Latent Decompositioncited by 42
  9. 2024SemlaFlow -- Efficient 3D Molecular Generation with Latent Attention and Equivariant Flow Matchingcited by 41
  10. 20233D molecule generation by denoising voxel gridscited by 40
  11. 2024Equivariant Graph Neural Operator for Modeling 3D Dynamicscited by 38
  12. 2023UGG: Unified Generative Graspingcited by 30
38 more
  1. 2025A Simple and Effective Reinforcement Learning Method for Text-to-Image Diffusion Fine-tuningcited by 30
  2. 2023UniGS: Unified Representation for Image Generation and Segmentationcited by 29
  3. 2024A Survey of Generative AI for de novo Drug Design: New Frontiers in Molecule and Protein Generationcited by 29
  4. 2024A Survey of Geometric Graph Neural Networks: Data Structures, Models and Applicationscited by 28
  5. 2025Scenario Dreamer: Vectorized Latent Diffusion for Generating Driving Simulation Environmentscited by 28
  6. 2024SLEDGE: Synthesizing Driving Environments with Generative Models and Rule-Based Trafficcited by 27
  7. 2024Diffusion Models in textitDe Novo Drug Designcited by 26
  8. 2024Unifying Generation and Prediction on Graphs with Latent Graph Diffusioncited by 25
  9. 2024Training Free Guided Flow Matching with Optimal Controlcited by 25
  10. 2023MOFDiff: Coarse-grained Diffusion for Metal-Organic Framework Designcited by 24
  11. 2024UniGEM: A Unified Approach to Generation and Property Prediction for Moleculescited by 21
  12. 2024Hyperbolic Geometric Latent Diffusion Model for Graph Generationcited by 20
  13. 2024Beyond Euclid: An Illustrated Guide to Modern Machine Learning with Geometric, Topological, and Algebraic Structurescited by 20
  14. 2024Structure-based drug design by denoising voxel gridscited by 19
  15. 2024Equivariance via Minimal Frame Averaging for More Symmetries and Efficiencycited by 19
  16. 2024Unified Generative Modeling of 3D Molecules via Bayesian Flow Networkscited by 18
  17. 2024Are High-Degree Representations Really Unnecessary in Equivariant Graph Neural Networks?cited by 18
  18. 2025NExT-Mol: 3D Diffusion Meets 1D Language Modeling for 3D Molecule Generationcited by 17
  19. 2025A Periodic Bayesian Flow for Material Generationcited by 16
  20. 2024Geometric Trajectory Diffusion Modelscited by 15
  21. 2025Multi-domain Distribution Learning for De Novo Drug Designcited by 15
  22. 2024Geometric Representation Condition Improves Equivariant Molecule Generationcited by 13
  23. 2025Electron flow matching for generative reaction mechanism prediction obeying conservation lawscited by 13
  24. 2025Applications of Modular Co-Design for De Novo 3D Molecule Generationcited by 13
  25. 2025Equivariant Neural Diffusion for Molecule Generationcited by 13
  26. 2024Geometric-Facilitated Denoising Diffusion Model for 3D Molecule Generationcited by 12
  27. 2024Latent Diffusion for Neural Spiking Datacited by 12
  28. 2025TABASCO: A Fast, Simplified Model for Molecular Generation with Improved Physical Qualitycited by 12
  29. 2024Accelerating 3D Molecule Generation via Jointly Geometric Optimal Transportcited by 11
  30. 2024LDMol: A Text-to-Molecule Diffusion Model with Structurally Informative Latent Space Surpasses AR Modelscited by 11
  31. 2024Context-Guided Diffusion for Out-of-Distribution Molecular and Protein Designcited by 11
  32. 2025DIFFVSGG: Diffusion-Driven Online Video Scene Graph Generationcited by 11
  33. 2023Discrete Graph Auto-Encodercited by 10
  34. 2024Geometry Informed Tokenization of Molecules for Language Model Generationcited by 10
  35. 2025Platonic Transformers: A Solid Choice For Equivariancecited by 10
  36. 2023Towards Joint Sequence-Structure Generation of Nucleic Acid and Protein Complexes with SE(3)-Discrete Diffusioncited by 9
  37. 2024Molecular relaxation by reverse diffusion with time step predictioncited by 9
  38. 2025Unified Guidance for Geometry-Conditioned Molecular Generationcited by 9

50 most cited of 186 All 186 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2023Geometry-Complete Diffusion for 3D Molecule Generation and Optimization
  2. 2022MDM: Molecular Diffusion Model for 3D Molecule Generation
  3. 2025Towards Unified and Lossless Latent Space for 3D Molecular Latent Diffusion Modeling
  4. 2023Navigating the Design Space of Equivariant Diffusion-Based Generative Models for De Novo 3D Molecule Generation
  5. 2025D3MES: Diffusion Transformer with multihead equivariant self-attention for 3D molecule generation
  6. 2024Accelerating the Generation of Molecular Conformations with Progressive Distillation of Equivariant Latent Diffusion Models
  7. 2022DiffMD: A Geometric Diffusion Model for Molecular Dynamics Simulations
  8. 2025Exploring Molecule Generation Using Latent Space Graph Diffusion