mlsanityData to 7 Oct 2026

Unraveling the Potential of Diffusion Models in Small Molecule Generation

arXiv 2507.08005 ↗First posted 25 Jun 2025q-bio.BM cs.AI cs.LGcited by 3

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

Abstract (arXiv)

Generative AI presents chemists with novel ideas for drug design and facilitates the exploration of vast chemical spaces. Diffusion models (DMs), an emerging tool, have recently attracted great attention in drug R&D. This paper comprehensively reviews the latest advancements and applications of DMs in molecular generation. It begins by introducing the theoretical principles of DMs. Subsequently, it categorizes various DM-based molecular generation methods according to their mathematical and chemical applications. The review further examines the performance of these models on benchmark datasets, with a particular focus on comparing the generation performance of existing 3D methods. Finally, it concludes by emphasizing current challenges and suggesting future research directions to fully exploit the potential of DMs in drug discovery.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Placed in Flow matching, time series and science, one of 14 directions in Diffusion models. Builds on 52 of its 85 references that are in the map. First posted on arXiv 25 Jun 2025.

Builds on

52 of 85 references.

Closest ancestors · 20

Same direction, newest first

  1. 2024Aligning Target-Aware Molecule Diffusion Models with Exact Energy Optimization1 Jul
  2. 2024AUTODIFF: Autoregressive Diffusion Modeling for Structure-based Drug Design2 Apr
  3. 2024DecompOpt: Controllable and Decomposed Diffusion Models for Structure-based Molecular Optimization7 Mar
  4. 2024Text-Guided Molecule Generation with Diffusion Language Model20 Feb
  5. 2024Binding-Adaptive Diffusion Models for Structure-Based Drug Design15 Jan
  6. 2024Geometric-Facilitated Denoising Diffusion Model for 3D Molecule Generation5 Jan
  7. 2023Autoregressive fragment-based diffusion for pocket-aware ligand design15 Dec
  8. 2023Swallowing the Bitter Pill: Simplified Scalable Conformer Generation27 Nov
  9. 2023Navigating the Design Space of Equivariant Diffusion-Based Generative Models for De Novo 3D Molecule Generation29 Sep
  10. 2023Coarse-to-Fine: a Hierarchical Diffusion Model for Molecule Generation in 3D5 May
  11. 2023Geometric Latent Diffusion Models for 3D Molecule Generation2 May
  12. 2023SILVR: Guided Diffusion for Molecule Generation21 Apr
8 more
  1. 2023MiDi: Mixed Graph and 3D Denoising Diffusion for Molecule Generation17 Feb
  2. 2022Structure-based Drug Design with Equivariant Diffusion Models24 Oct
  3. 2022Equivariant 3D-Conditional Diffusion Models for Molecular Linker Design11 Oct
  4. 2022Flow Matching for Generative Modeling6 Oct
  5. 2022DiGress: Discrete Denoising diffusion for graph generation29 Sep
  6. 2022MDM: Molecular Diffusion Model for 3D Molecule Generation13 Sep
  7. 2022Equivariant Diffusion for Molecule Generation in 3D31 Mar
  8. 2022GeoDiff: a Geometric Diffusion Model for Molecular Conformation Generation6 Mar

Other references · 32

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2022Training language models to follow instructions with human feedbackcited by 15,712
  4. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  5. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  6. 2022Classifier-Free Diffusion Guidancecited by 5,717
  7. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  8. 2018Graph Neural Networks: A Review of Methods and Applicationscited by 1,571
  9. 2022RePaint: Inpainting using Denoising Diffusion Probabilistic Modelscited by 1,419
  10. 2022Diffusion-LM Improves Controllable Text Generationcited by 1,006
  11. 2021E(n) Equivariant Graph Neural Networkscited by 951
  12. 2018Junction Tree Variational Autoencoder for Molecular Graph Generationcited by 647
20 more
  1. 2021ILVR: Conditioning Method for Denoising Diffusion Probabilistic Modelscited by 634
  2. 2020SE(3)-Transformers: 3D Roto-Translation Equivariant Attention Networkscited by 602
  3. 2018MolGAN: An implicit generative model for small molecular graphscited by 392
  4. 2018GraphVAE: Towards Generation of Small Graphs Using Variational Autoencoderscited by 375
  5. 2022Analog Bits: Generating Discrete Data using Diffusion Models with Self-Conditioningcited by 362
  6. 2022DiffDock: Diffusion Steps, Twists, and Turns for Molecular Dockingcited by 307
  7. 2018GuacaMol: Benchmarking Models for De Novo Molecular Designcited by 294
  8. 2024Fast High-Resolution Image Synthesis with Latent Adversarial Diffusion Distillationcited by 276
  9. 2022Torsional Diffusion for Molecular Conformer Generationcited by 262
  10. 2020GEOM: Energy-annotated molecular conformations for property prediction and molecular generationcited by 238
  11. 2022Translation between Molecules and Natural Languagecited by 173
  12. 2021E(n) Equivariant Normalizing Flowscited by 165
  13. 2022Generating 3D Molecules for Target Protein Bindingcited by 104
  14. 2023MolDiff: Addressing the Atom-Bond Inconsistency Problem in 3D Molecule Diffusion Generationcited by 65
  15. 2023MUDiff: Unified Diffusion for Complete Molecule Generationcited by 41
  16. 20233D molecule generation by denoising voxel gridscited by 38
  17. 2024Re-Dock: Towards Flexible and Realistic Molecular Docking with Diffusion Bridgecited by 16
  18. 2023Classifier-free graph diffusion for molecular property targetingcited by 13
  19. 2023Shape-conditioned 3D Molecule Generation via Equivariant Diffusion Modelscited by 7
  20. 2023STRIDE: Structure-guided Generation for Inverse Design of Moleculescited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 2; 2026: 1.

3 papers.

Similar, not cited

Close in wording, no citation either way

  1. 2025Diffusion Models for Molecules: A Survey of Methods and Tasks
  2. 2024Diffusion Models in textitDe Novo Drug Design
  3. 2023Diffusing on Two Levels and Optimizing for Multiple Properties: A Novel Approach to Generating Molecules with Desirable Properties
  4. 2026A Systematic Evaluation of Molecule Generation Models for De Novo Drug Design: From Benchmarks to Practical Insights
  5. 2024Text-guided Diffusion Model for 3D Molecule Generation
  6. 2026Autoregressive latent diffusion for 3D molecule generation
  7. 2022Diffusion-based Molecule Generation with Informative Prior Bridges
  8. 2025D3MES: Diffusion Transformer with multihead equivariant self-attention for 3D molecule generation