mlsanityData to 7 Oct 2026

Text-guided Diffusion Model for 3D Molecule Generation

arXiv 2410.03803 ↗First posted 4 Oct 2024cs.LG cs.AI physics.chem-phcited by 5

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

Abstract (arXiv)

The de novo generation of molecules with targeted properties is crucial in biology, chemistry, and drug discovery. Current generative models are limited to using single property values as conditions, struggling with complex customizations described in detailed human language. To address this, we propose the text guidance instead, and introduce TextSMOG, a new Text-guided Small Molecule Generation Approach via 3D Diffusion Model which integrates language and diffusion models for text-guided small molecule generation. This method uses textual conditions to guide molecule generation, enhancing both stability and diversity. Experimental results show TextSMOG's proficiency in capturing and utilizing information from textual descriptions, making it a powerful tool for generating 3D molecular structures in response to complex textual customizations.

Key facts. Cited by 5 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 54 of its 81 references that are in the map. First posted on arXiv 4 Oct 2024.

Builds on

54 of 81 references.

Closest ancestors · 2

Same direction, newest first

  1. 2022MDM: Molecular Diffusion Model for 3D Molecule Generation13 Sep
  2. 2022GeoDiff: a Geometric Diffusion Model for Molecular Conformation Generation6 Mar

Other references · 52

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  4. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  5. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  6. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  7. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  8. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  9. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  10. 2017Inductive Representation Learning on Large Graphscited by 6,284
  11. 2018How Powerful are Graph Neural Networks?cited by 4,355
  12. 2022DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generationcited by 3,286
38 more
  1. 2021Image Super-Resolution via Iterative Refinementcited by 1,506
  2. 2019SciBERT: A Pretrained Language Model for Scientific Textcited by 1,404
  3. 2020DiffWave: A Versatile Diffusion Model for Audio Synthesiscited by 1,339
  4. 2018Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point cloudscited by 735
  5. 2018Junction Tree Variational Autoencoder for Molecular Graph Generationcited by 647
  6. 2021ILVR: Conditioning Method for Denoising Diffusion Probabilistic Modelscited by 634
  7. 2020WaveGrad: Estimating Gradients for Waveform Generationcited by 620
  8. 2020SE(3)-Transformers: 3D Roto-Translation Equivariant Attention Networkscited by 602
  9. 2018GraphVAE: Towards Generation of Small Graphs Using Variational Autoencoderscited by 375
  10. 2020GraphAF: a Flow-based Autoregressive Model for Molecular Graph Generationcited by 301
  11. 2017Grammar Variational Autoencodercited by 283
  12. 2022Torsional Diffusion for Molecular Conformer Generationcited by 262
  13. 2020Generalizing Convolutional Neural Networks for Equivariance to Lie Groups on Arbitrary Continuous Datacited by 248
  14. 2020Equivariant Flows: Exact Likelihood Generative Learning for Symmetric Densitiescited by 248
  15. 2021Pre-training Molecular Graph Representation with 3D Geometrycited by 248
  16. 2020MoFlow: An Invertible Flow Model for Generating Molecular Graphscited by 183
  17. 2018Constrained Graph Variational Autoencoders for Molecule Designcited by 182
  18. 2021GraphDF: A Discrete Flow Model for Molecular Graph Generationcited by 177
  19. 2019Symmetry-adapted generation of 3d point sets for the targeted discovery of moleculescited by 171
  20. 2021E(n) Equivariant Normalizing Flowscited by 165
  21. 2022A Molecular Multimodal Foundation Model Associating Molecule Graphs with Natural Languagecited by 129
  22. 2023MolCA: Molecular Graph-Language Modeling with Cross-Modal Projector and Uni-Modal Adaptercited by 128
  23. 2019GraphNVP: An Invertible Flow Model for Generating Molecular Graphscited by 115
  24. 2022Diffusion-based Molecule Generation with Informative Prior Bridgescited by 104
  25. 2018Syntax-Directed Variational Autoencoder for Structured Datacited by 103
  26. 2021Inverse design of 3d molecular structures with conditional generative neural networkscited by 93
  27. 2019Molecular geometry prediction using a deep generative graph neural networkcited by 91
  28. 2019MolecularRNN: Generating realistic molecular graphs with optimized propertiescited by 80
  29. 2022Equivariant Energy-Guided SDE for Inverse Molecular Designcited by 72
  30. 2021Keeping it Simple: Language Models can learn Complex Molecular Distributionscited by 68
  31. 2024Towards 3D Molecule-Text Interpretation in Language Modelscited by 65
  32. 2023Rethinking Tokenizer and Decoder in Masked Graph Modeling for Moleculescited by 49
  33. 2018Conditional molecular design with deep generative modelscited by 44
  34. 2024ProtT3: Protein-to-Text Generation for Text-based Protein Understandingcited by 25
  35. 2018DEFactor: Differentiable Edge Factorization-based Probabilistic Graph Generationcited by 24
  36. 2024MolTC: Towards Molecular Relational Modeling In Language Modelscited by 22
  37. 2019Generating valid Euclidean distance matricescited by 19
  38. 20203DMolNet: A Generative Network for Molecular Structurescited by 19

50 most cited of 52 All 52 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 3; 2026: 1.

5 papers.

  1. 2025NExT-Mol: 3D Diffusion Meets 1D Language Modeling for 3D Molecule Generationcited by 17
  2. 2025Periodic Materials Generation using Text-Guided Joint Diffusion Modelcited by 15
  3. 2024Diffusion Twigs with Loop Guidance for Conditional Graph Generationcited by 4
  4. 2025GeoAda: Efficiently Finetune Geometric Diffusion Models with Equivariant Adapterscited by 1
  5. 2026Agentic Molecular Recovery via Molecule-Aware Explorationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Text-Guided Molecule Generation with Diffusion Language Model
  2. 20243M-Diffusion: Latent Multi-Modal Diffusion for Language-Guided Molecular Structure Generation
  3. 2024LDMol: A Text-to-Molecule Diffusion Model with Structurally Informative Latent Space Surpasses AR Models
  4. 2025Chain-of-Generation: Progressive Latent Diffusion for Text-Guided Molecular Design
  5. 2023Coarse-to-Fine: a Hierarchical Diffusion Model for Molecule Generation in 3D
  6. 2025Unraveling the Potential of Diffusion Models in Small Molecule Generation
  7. 2024Crossing New Frontiers: Knowledge-Augmented Large Language Model Prompting for Zero-Shot Text-Based De Novo Molecule Design
  8. 2024Instruction-Based Molecular Graph Generation with Unified Text-Graph Diffusion Model