mlsanityData to 7 Oct 2026

3D molecule generation by denoising voxel grids

arXiv 2306.07473 ↗First posted 13 Jun 2023cs.LG q-bio.QMcited by 38

Not on the map. Why?

Abstract (arXiv)

We propose a new score-based approach to generate 3D molecules represented as atomic densities on regular grids. First, we train a denoising neural network that learns to map from a smooth distribution of noisy molecules to the distribution of real molecules. Then, we follow the neural empirical Bayes framework (Saremi and Hyvarinen, 19) and generate molecules in two steps: (i) sample noisy density grids from a smooth distribution via underdamped Langevin Markov chain Monte Carlo, and (ii) recover the "clean" molecule by denoising the noisy grid with a single step. Our method, VoxMol, generates molecules in a fundamentally different way than the current state of the art (ie, diffusion models applied to atom point clouds). It differs in terms of the data representation, the noise model, the network architecture and the generative modeling algorithm. Our experiments show that VoxMol captures the distribution of drug-like molecules better than state of the art, while being faster to generate samples.

Key facts. Cited by 38 papers in the map (data through 7 Oct 2026). Builds on 65 of its 98 references that are in the map. First posted on arXiv 13 Jun 2023.

Builds on

65 of 98 references.

References · 65

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  4. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  5. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  6. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  7. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  8. 2018How Powerful are Graph Neural Networks?cited by 4,355
  9. 2013Auto-Encoding Variational Bayescited by 3,980
  10. 2015Variational Inference with Normalizing Flowscited by 2,161
  11. 2018Group Normalizationcited by 1,514
  12. 2017MoleculeNet: A Benchmark for Molecular Machine Learningcited by 1,037
38 more
  1. 2021E(n) Equivariant Graph Neural Networkscited by 951
  2. 2017Sigmoid-Weighted Linear Units for Neural Network Function Approximation in Reinforcement Learningcited by 935
  3. 2018Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networkscited by 878
  4. 2018Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point cloudscited by 735
  5. 2022Equivariant Diffusion for Molecule Generation in 3Dcited by 666
  6. 2018Junction Tree Variational Autoencoder for Molecular Graph Generationcited by 647
  7. 2022GeoDiff: a Geometric Diffusion Model for Molecular Conformation Generationcited by 511
  8. 2022MACE: Higher Order Equivariant Message Passing Neural Networks for Fast and Accurate Force Fieldscited by 467
  9. 2019Provably Powerful Graph Networkscited by 385
  10. 20183D Steerable CNNs: Learning Rotationally Equivariant Features in Volumetric Datacited by 348
  11. 2019Point-Voxel CNN for Efficient 3D Deep Learningcited by 343
  12. 2020Learning from Protein Structure with Geometric Vector Perceptronscited by 308
  13. 2022DiffDock: Diffusion Steps, Twists, and Turns for Molecular Dockingcited by 307
  14. 2022Torsional Diffusion for Molecular Conformer Generationcited by 262
  15. 2022Equiformer: Equivariant Graph Attention Transformer for 3D Atomistic Graphscited by 258
  16. 2020Equivariant Flows: Exact Likelihood Generative Learning for Symmetric Densitiescited by 248
  17. 2014Understanding image representations by measuring their equivariance and equivalencecited by 240
  18. 2020GEOM: Energy-annotated molecular conformations for property prediction and molecular generationcited by 238
  19. 2018Learning Deep Generative Models of Graphscited by 227
  20. 2022Structure-based Drug Design with Equivariant Diffusion Modelscited by 213
  21. 2023Geometric Latent Diffusion Models for 3D Molecule Generationcited by 185
  22. 2022Pocket2Mol: Efficient Molecular Sampling Based on 3D Protein Pocketscited by 182
  23. 20233D Equivariant Diffusion for Target-Aware Molecule Generation and Affinity Predictioncited by 176
  24. 2019Symmetry-adapted generation of 3d point sets for the targeted discovery of moleculescited by 171
  25. 2022e3nn: Euclidean Neural Networkscited by 171
  26. 2021E(n) Equivariant Normalizing Flowscited by 165
  27. 2021Learning Gradient Fields for Molecular Conformation Generationcited by 162
  28. 2017Underdamped Langevin MCMC: A non-asymptotic analysiscited by 131
  29. 2022Equivariant 3D-Conditional Diffusion Models for Molecular Linker Designcited by 121
  30. 2017Objective-Reinforced Generative Adversarial Networks (ORGAN) for Sequence Generation Modelscited by 116
  31. 2021GeoMol: Torsional Geometric Generation of Molecular 3D Conformer Ensemblescited by 106
  32. 2022Diffusion-based Molecule Generation with Informative Prior Bridgescited by 104
  33. 2023MiDi: Mixed Graph and 3D Denoising Diffusion for Molecule Generationcited by 96
  34. 2019Molecular geometry prediction using a deep generative graph neural networkcited by 91
  35. 2019A Generative Model for Molecular Distance Geometrycited by 73
  36. 2020ATOM3D: Tasks On Molecules in Three Dimensionscited by 73
  37. 2021Generating 3D Molecules Conditional on Receptor Binding Sites with Deep Generative Modelscited by 72
  38. 2023Language models can generate molecules, materials, and protein binding sites directly in three dimensions as XYZ, CIF, and PDB filescited by 59

50 most cited of 65 All 65 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 13; 2025: 15; 2026: 9.

38 papers.

Sort:

By area:

  1. 2025All-atom Diffusion Transformers: Unified generative modelling of molecules and materialscited by 75
  2. 2023Swallowing the Bitter Pill: Simplified Scalable Conformer Generationcited by 55
  3. 2024RGFN: Synthesizable Molecular Generation Using GFlowNetscited by 39
  4. 2024CBGBench: Fill in the Blank of Protein-Molecule Complex Binding Graphcited by 19
  5. 2024Structure-based drug design by denoising voxel gridscited by 18
  6. 2025Applications of Modular Co-Design for De Novo 3D Molecule Generationcited by 13
  7. 2025Equivariant Neural Diffusion for Molecule Generationcited by 13
  8. 20243D Vessel Graph Generation Using Denoising Diffusioncited by 9
  9. 2025Scalable Autoregressive 3D Molecule Generationcited by 7
  10. 2024E(3)-equivariant models cannot learn chirality: Field-based molecular generationcited by 6
  11. 2024Tactile DreamFusion: Exploiting Tactile Sensing for 3D Generationcited by 6
  12. 2025Unified Cross-Scale 3D Generation and Understanding via Autoregressive Modelingcited by 5
26 more
  1. 2026Molecular Representations in Implicit Functional Space via Hyper-Networkscited by 5
  2. 2024Cell Morphology-Guided Small Molecule Generation with GFlowNetscited by 4
  3. 2024JAMUN: Bridging Smoothed Molecular Dynamics and Score-Based Learning for Conformational Ensemblescited by 4
  4. 2025ProxelGen: Generating Proteins as 3D Densitiescited by 4
  5. 2024NEBULA: Neural Empirical Bayes Under Latent Representations for Efficient and Controllable Design of Molecular Librariescited by 3
  6. 2024A noise-corrected Langevin algorithm and sampling by half-denoisingcited by 3
  7. 2025Manipulating 3D Molecules in a Fixed-Dimensional E(3)-Equivariant Latent Spacecited by 3
  8. 2025Unraveling the Potential of Diffusion Models in Small Molecule Generationcited by 3
  9. 20263D Molecule Generation from Rigid Motifs via SE(3) Flowscited by 3
  10. 2024Diffusion-based Graph Generative Methodscited by 2
  11. 2024nach0-pc: Multi-task Language Model with Molecular Point Cloud Encodercited by 2
  12. 2025Do we need equivariant models for molecule generation?cited by 2
  13. 2025Controllable 3D Molecular Generation for Structure-Based Drug Design Through Bayesian Flow Networks and Gradient Integrationcited by 2
  14. 2025Unified all-atom molecule generation with neural fieldscited by 2
  15. 2026Generative Molecular Morphing for Flexible-Size Design via Unbalanced Optimal Transportcited by 2
  16. 2024Grand canonical generative diffusion model for crystalline phases and grain boundariescited by 1
  17. 2025Training Dynamics of Learning 3D-Rotational Equivariancecited by 1
  18. 2026CORDS: Continuous Representations of Discrete Structurescited by 1
  19. 2026VecMol: Vector-Field Representations for 3D Molecule Generationcited by 1
  20. 2025Learning Deformable Body Interactions With Adaptive Spatial Tokenizationcited by 0
  21. 2025HyperDiffusionFields (HyDiF): Diffusion-Guided Hypernetworks for Learning Implicit Molecular Neural Fieldscited by 0
  22. 2025Beyond Atoms: Evaluating Electron Density Representation for 3D Molecular Learningcited by 0
  23. 2026Latent Diffusion-Based 3D Molecular Recovery from Vibrational Spectracited by 0
  24. 2026Sesame: Structure-Aware Molecular Generation via Spatial Density-Map Conditioningcited by 0
  25. 2026SynLaD: Latent Diffusion for Generating Synthesizable Molecules Conditioned on 3D Pharmacophore Profilescited by 0
  26. 2026A Systematic Evaluation of Molecule Generation Models for De Novo Drug Design: From Benchmarks to Practical Insightscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023Geometry-Complete Diffusion for 3D Molecule Generation and Optimization
  2. 2024Geometric-Facilitated Denoising Diffusion Model for 3D Molecule Generation
  3. 2026Breaking the Bottlenecks: Scalable Diffusion Models for 3D Molecular Generation
  4. 2024Diffusion Models in textitDe Novo Drug Design
  5. 2023MolDiff: Addressing the Atom-Bond Inconsistency Problem in 3D Molecule Diffusion Generation
  6. 2023Coarse-to-Fine: a Hierarchical Diffusion Model for Molecule Generation in 3D
  7. 2024A survey of probabilistic generative frameworks for molecular simulations
  8. 2026Autoregressive latent diffusion for 3D molecule generation