mlsanityData to 7 Oct 2026

MolDiff: Addressing the Atom-Bond Inconsistency Problem in 3D Molecule Diffusion Generation

arXiv 2305.07508 ↗First posted 11 May 2023q-bio.BM cs.LG q-bio.QMcited by 65

Not on the map. Why?

Cited by 34 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Deep generative models have recently achieved superior performance in 3D molecule generation. Most of them first generate atoms and then add chemical bonds based on the generated atoms in a post-processing manner. However, there might be no corresponding bond solution for the temporally generated atoms as their locations are generated without considering potential bonds. We define this problem as the atom-bond inconsistency problem and claim it is the main reason for current approaches to generating unrealistic 3D molecules. To overcome this problem, we propose a new diffusion model called MolDiff which can generate atoms and bonds simultaneously while still maintaining their consistency by explicitly modeling the dependence between their relationships. We evaluated the generation ability of our proposed model and the quality of the generated molecules using criteria related to both geometry and chemical properties. The empirical studies showed that our model outperforms previous approaches, achieving a three-fold improvement in success rate and generating molecules with significantly better quality.

Key facts. Cited by 65 papers in the map (data through 7 Oct 2026). Builds on 38 of its 47 references that are in the map. First posted on arXiv 11 May 2023.

Builds on

38 of 47 references.

References · 38

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  3. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  4. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,539
  5. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  6. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,736
  7. 2021Structured Denoising Diffusion Models in Discrete State-Spacescited by 1,665
  8. 2021E(n) Equivariant Graph Neural Networkscited by 951
  9. 2016Automatic chemical design using a data-driven continuous representation of moleculescited by 762
  10. 2022Equivariant Diffusion for Molecule Generation in 3Dcited by 666
  11. 2018Junction Tree Variational Autoencoder for Molecular Graph Generationcited by 647
  12. 2021Argmax Flows and Multinomial Diffusion: Learning Categorical Distributionscited by 566
26 more
  1. 2018Predictive Uncertainty Estimation via Prior Networkscited by 555
  2. 2022GeoDiff: a Geometric Diffusion Model for Molecular Conformation Generationcited by 511
  3. 2022DiGress: Discrete Denoising diffusion for graph generationcited by 503
  4. 2018Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generationcited by 363
  5. 2020GraphAF: a Flow-based Autoregressive Model for Molecular Graph Generationcited by 301
  6. 2017Grammar Variational Autoencodercited by 283
  7. 2022Score-based Generative Modeling of Graphs via the System of Stochastic Differential Equationscited by 273
  8. 2020Permutation Invariant Graph Generation via Score-Based Generative Modelingcited by 263
  9. 2020GEOM: Energy-annotated molecular conformations for property prediction and molecular generationcited by 238
  10. 2022Structure-based Drug Design with Equivariant Diffusion Modelscited by 213
  11. 2018Optimization of Molecules via Deep Reinforcement Learningcited by 199
  12. 2018Constrained Graph Variational Autoencoders for Molecule Designcited by 182
  13. 2022Pocket2Mol: Efficient Molecular Sampling Based on 3D Protein Pocketscited by 182
  14. 20233D Equivariant Diffusion for Target-Aware Molecule Generation and Affinity Predictioncited by 176
  15. 2019Symmetry-adapted generation of 3d point sets for the targeted discovery of moleculescited by 171
  16. 2021E(n) Equivariant Normalizing Flowscited by 165
  17. 2022A 3D Generative Model for Structure-Based Drug Designcited by 148
  18. 2022Equivariant 3D-Conditional Diffusion Models for Molecular Linker Designcited by 121
  19. 2022Generating 3D Molecules for Target Protein Bindingcited by 104
  20. 2022Diffusion-based Molecule Generation with Informative Prior Bridgescited by 104
  21. 2023MiDi: Mixed Graph and 3D Denoising Diffusion for Molecule Generationcited by 96
  22. 2022Diffusion Models for Graphs Benefit From Discrete State Spacescited by 69
  23. 2022DiffBP: Generative Diffusion of 3D Molecules for Target Protein Bindingcited by 58
  24. 2021Learning to design drug-like molecules in three-dimensional space using deep generative modelscited by 37
  25. 2020Learning a Continuous Representation of 3D Molecular Structures with Deep Generative Modelscited by 24
  26. 2020Multi-Objective Molecule Generation using Interpretable Substructurescited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 6; 2024: 21; 2025: 21; 2026: 17.

65 papers.

Sort:

By area:

  1. 2024Generative Flows on Discrete State-Spaces: Enabling Multimodal Flows with Applications to Protein Co-Designcited by 294
  2. 2023On the Design Fundamentals of Diffusion Models: A Surveycited by 59
  3. 2023Enhancing Deep Reinforcement Learning: A Tutorial on Generative Diffusion Models in Network Optimizationcited by 56
  4. 2024Mixed Continuous and Categorical Flow Matching for 3D De Novo Molecule Generationcited by 53
  5. 2023Navigating the Design Space of Equivariant Diffusion-Based Generative Models for De Novo 3D Molecule Generationcited by 50
  6. 2024MolCRAFT: Structure-Based Drug Design in Continuous Parameter Spacecited by 48
  7. 2023AlignDiff: Aligning Diverse Human Preferences via Behavior-Customisable Diffusion Modelcited by 37
  8. 2024A Survey of Geometric Graph Neural Networks: Data Structures, Models and Applicationscited by 28
  9. 2024Diffusion Models in textitDe Novo Drug Designcited by 26
  10. 2025FlowMol3: Flow Matching for 3D De Novo Small-Molecule Generationcited by 20
  11. 2024Unified Generative Modeling of 3D Molecules via Bayesian Flow Networkscited by 18
  12. 2025Flow Matching Meets Biology and Life Science: A Surveycited by 14
38 more
  1. 2025Applications of Modular Co-Design for De Novo 3D Molecule Generationcited by 13
  2. 2025Equivariant Neural Diffusion for Molecule Generationcited by 13
  3. 2024TAGMol: Target-Aware Gradient-guided Molecule Generationcited by 12
  4. 2024BindGPT: A Scalable Framework for 3D Molecular Design via Language Modeling and Reinforcement Learningcited by 12
  5. 2025Large Language Model Agent for Modular Task Execution in Drug Discoverycited by 12
  6. 2024Accelerating 3D Molecule Generation via Jointly Geometric Optimal Transportcited by 11
  7. 2024Context-Guided Diffusion for Out-of-Distribution Molecular and Protein Designcited by 11
  8. 2025Generating 3D Binding Molecules Using Shape-Conditioned Diffusion Models with Guidancecited by 10
  9. 2024Molecular relaxation by reverse diffusion with time step predictioncited by 9
  10. 20243D Vessel Graph Generation Using Denoising Diffusioncited by 9
  11. 2025Straight-Line Diffusion Model for Efficient 3D Molecular Generationcited by 8
  12. 2023Shape-conditioned 3D Molecule Generation via Equivariant Diffusion Modelscited by 7
  13. 2024Generative Inverse Design of Crystal Structures via Diffusion Models with Transformerscited by 7
  14. 2024Decomposed Direct Preference Optimization for Structure-Based Drug Designcited by 7
  15. 2024Zero Shot Molecular Generation via Similarity Kernelscited by 6
  16. 2024E(3)-equivariant models cannot learn chirality: Field-based molecular generationcited by 6
  17. 2025Piloting Structure-Based Drug Design via Modality-Specific Optimal Schedulecited by 6
  18. 2025TFG-Flow: Training-free Guidance in Multimodal Generative Flowcited by 4
  19. 2024Regressor-free Molecule Generation to Support Drug Response Predictioncited by 3
  20. 2024TurboHopp: Accelerated Molecule Scaffold Hopping with Consistency Modelscited by 3
  21. 2025Disentangling Total-Variance and Signal-to-Noise-Ratio Improves Diffusion Modelscited by 3
  22. 2025Unraveling the Potential of Diffusion Models in Small Molecule Generationcited by 3
  23. 20263D Molecule Generation from Rigid Motifs via SE(3) Flowscited by 3
  24. 2026Elign: Equivariant Diffusion Model Alignment from Foundational Machine Learning Force Fieldscited by 3
  25. 2023STRIDE: Structure-guided Generation for Inverse Design of Moleculescited by 2
  26. 2025HybridLinker: Topology-Guided Posterior Sampling for Enhanced Diversity and Validity in 3D Molecular Linker Generationcited by 2
  27. 2025Controllable 3D Molecular Generation for Structure-Based Drug Design Through Bayesian Flow Networks and Gradient Integrationcited by 2
  28. 2025MolChord: Structure-Sequence Alignment for Protein-Guided Drug Designcited by 2
  29. 2025NEAT: Neighborhood-Guided, Efficient, Autoregressive Set Transformer for 3D Molecular Generationcited by 2
  30. 2024Response Matching for generating materials and moleculescited by 1
  31. 2025Interleaved Gibbs Diffusion: Generating Discrete-Continuous Data with Implicit Constraintscited by 1
  32. 2025Full-Atom Peptide Design via Riemannian-Euclidean Bayesian Flow Networkscited by 1
  33. 2026FuseDiff: Symmetry-Preserving Joint Diffusion for Dual-Target Structure-Based Drug Designcited by 1
  34. 2026FlowMS: Flow Matching for De Novo Structure Elucidation from Mass Spectracited by 1
  35. 2026Generative Pseudo-Force Fields for Molecular Generationcited by 1
  36. 2026MolSafeEval: A Benchmark for Uncovering Safety Risks in AI-Generated Moleculescited by 1
  37. 2026Generating Developable 3D Molecules via Pocket-Conditioned Diffusion and Property-Aware Optimizationcited by 1
  38. 2024Distributional Priors Guided Diffusion for Generating 3D Molecules in Low Data Regimescited by 0

50 most cited of 65 All 65 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2022MDM: Molecular Diffusion Model for 3D Molecule Generation
  2. 2023Learning Joint 2D & 3D Diffusion Models for Complete Molecule Generation
  3. 2024Geometric-Facilitated Denoising Diffusion Model for 3D Molecule Generation
  4. 2023Geometric Latent Diffusion Models for 3D Molecule Generation
  5. 2025D3MES: Diffusion Transformer with multihead equivariant self-attention for 3D molecule generation
  6. 20233D molecule generation by denoising voxel grids
  7. 2024LMDM:Latent Molecular Diffusion Model For 3D Molecule Generation
  8. 2026Autoregressive latent diffusion for 3D molecule generation