mlsanityData to 7 Oct 2026

Text-Guided Molecule Generation with Diffusion Language Model

arXiv 2402.13040 ↗First posted 20 Feb 2024cs.LG cs.AI cs.CEcited by 31

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

Abstract (arXiv)

Text-guided molecule generation is a task where molecules are generated to match specific textual descriptions. Recently, most existing SMILES-based molecule generation methods rely on an autoregressive architecture. In this work, we propose the Text-Guided Molecule Generation with Diffusion Language Model (TGM-DLM), a novel approach that leverages diffusion models to address the limitations of autoregressive methods. TGM-DLM updates token embeddings within the SMILES string collectively and iteratively, using a two-phase diffusion generation process. The first phase optimizes embeddings from random noise, guided by the text description, while the second phase corrects invalid SMILES strings to form valid molecular representations. We demonstrate that TGM-DLM outperforms MolT5-Base, an autoregressive model, without the need for additional data resources. Our findings underscore the remarkable effectiveness of TGM-DLM in generating coherent and precise molecules with specific properties, opening new avenues in drug discovery and related scientific domains. Code will be released at: https://github.com/Deno-V/tgm-dlm.

Key facts. Cited by 31 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 14 of its 37 references that are in the map. First posted on arXiv 20 Feb 2024.

Builds on

14 of 37 references.

References · 14

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  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. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  7. 2023Sparks of Artificial General Intelligence: Early experiments with GPT-4cited by 2,579
  8. 2020DiffWave: A Versatile Diffusion Model for Audio Synthesiscited by 1,339
  9. 2022Diffusion-LM Improves Controllable Text Generationcited by 1,006
  10. 2018Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generationcited by 363
  11. 2022DiffusionBERT: Improving Generative Masked Language Models with Diffusion Modelscited by 214
  12. 2022Graph neural networks for materials science and chemistrycited by 181
2 more
  1. 2022Multi-modal Molecule Structure-text Model for Text-based Retrieval and Editingcited by 165
  2. 2023Uncovering Neural Scaling Laws in Molecular Representation Learningcited by 23

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 6; 2025: 15; 2026: 10.

31 papers.

Sort:

By area:

  1. 2025A Survey on Diffusion Language Modelscited by 75
  2. 2024Leveraging Biomolecule and Natural Language through Multi-Modal Learning: A Surveycited by 16
  3. 2025Periodic Materials Generation using Text-Guided Joint Diffusion Modelcited by 15
  4. 2024LDMol: A Text-to-Molecule Diffusion Model with Structurally Informative Latent Space Surpasses AR Modelscited by 11
  5. 2024Text-guided multi-property molecular optimization with a diffusion language modelcited by 11
  6. 2024Beyond Efficiency: Molecular Data Pruning for Enhanced Generalizationcited by 9
  7. 2025MolSpectra: Pre-training 3D Molecular Representation with Multi-modal Energy Spectracited by 8
  8. 2025Simplifying Bayesian Optimization Via In-Context Direct Optimum Samplingcited by 7
  9. 2025How to Make Large Language Models Generate 100% Valid Molecules?cited by 4
  10. 2024Instruction-Based Molecular Graph Generation with Unified Text-Graph Diffusion Modelcited by 3
  11. 2025Unraveling the Potential of Diffusion Models in Small Molecule Generationcited by 3
  12. 2025MolEdit: Knowledge Editing for Multimodal Molecule Language Modelscited by 3
19 more
  1. 2026CombiMOTS: Combinatorial Multi-Objective Tree Search for Dual-Target Molecule Generationcited by 2
  2. 2025Diffusion-based Evolutionary Optimization for 3D Multi-Objective Molecular Generationcited by 1
  3. 2025Training Text-to-Molecule Models with Context-Aware Tokenizationcited by 1
  4. 2025Transport-Coupled Bayesian Flows for Molecular Graph Generationcited by 1
  5. 2026TrustLDM: Benchmarking Trustworthiness in Language Diffusion Modelscited by 1
  6. 2026MolSafeEval: A Benchmark for Uncovering Safety Risks in AI-Generated Moleculescited by 1
  7. 2024Chemical Language Model Linker: blending text and molecules with modular adapterscited by 0
  8. 2025Automatic Annotation Augmentation Boosts Translation between Molecules and Natural Languagecited by 0
  9. 2025TextOmics-Guided Diffusion for Hit-like Molecular Generationcited by 0
  10. 2025Cross-Modality Controlled Molecule Generation with Diffusion Language Modelcited by 0
  11. 2025Valid Property-Enhanced Contrastive Learning for Targeted Optimization & Resampling for Novel Drug Designcited by 0
  12. 2025Chain-of-Generation: Progressive Latent Diffusion for Text-Guided Molecular Designcited by 0
  13. 2026MolRGen: A Training and Evaluation Setting for De Novo Molecular Generation with Reasonning Modelscited by 0
  14. 2026MolDA: Molecular Understanding and Generation via Large Language Diffusion Modelcited by 0
  15. 2026BiMol-Diff: A Unified Diffusion Framework for Molecular Generation and Captioningcited by 0
  16. 2026Agentic Molecular Recovery via Molecule-Aware Explorationcited by 0
  17. 2026Gene Expression-Informed Jointly Controlled Generative Modeling for Precision Molecular Designcited by 0
  18. 2026HEDGEHOG: Hierarchical Evaluation of Drug Generators Through Rigorous Filtrationcited by 0
  19. 2026MolGVR: A Chemistry-Grounded Framework for Text-to-Molecule Generationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Text-guided Diffusion Model for 3D Molecule Generation
  2. 20243M-Diffusion: Latent Multi-Modal Diffusion for Language-Guided Molecular Structure Generation
  3. 2024Can LLMs Generate Diverse Molecules? Towards Alignment with Structural Diversity
  4. 2025NovoMolGen: Rethinking Molecular Language Model Pretraining
  5. 2026CAGenMol: Condition-Aware Diffusion Language Model for Goal-Directed Molecular Generation
  6. 2025Diffusion Models for Molecules: A Survey of Methods and Tasks
  7. 2025GenMol: A Drug Discovery Generalist with Discrete Diffusion
  8. 2026Autoregressive latent diffusion for 3D molecule generation