mlsanityData to 7 Oct 2026

DiscDiff: Latent Diffusion Model for DNA Sequence Generation

arXiv 2402.06079 ↗First posted 8 Feb 2024q-bio.GN cs.AI cs.LGcited by 12

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

Abstract (arXiv)

This paper introduces a novel framework for DNA sequence generation, comprising two key components: DiscDiff, a Latent Diffusion Model (LDM) tailored for generating discrete DNA sequences, and Absorb-Escape, a post-training algorithm designed to refine these sequences. Absorb-Escape enhances the realism of the generated sequences by correcting `round errors' inherent in the conversion process between latent and input spaces. Our approach not only sets new standards in DNA sequence generation but also demonstrates superior performance over existing diffusion models, in generating both short and long DNA sequences. Additionally, we introduce EPD-GenDNA, the first comprehensive, multi-species dataset for DNA generation, encompassing 160,000 unique sequences from 15 species. We hope this study will advance the generative modelling of DNA, with potential implications for gene therapy and protein production.

Key facts. Cited by 12 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 33 of its 58 references that are in the map. First posted on arXiv 8 Feb 2024.

Builds on

33 of 58 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023Dirichlet Diffusion Score Model for Biological Sequence Generation18 May

Other references · 32

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  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. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  7. 2020Denoising Diffusion Implicit Modelscited by 9,655
  8. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  9. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  10. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  11. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,616
  12. 2018UMAP: Uniform Manifold Approximation and Projection for Dimension Reductioncited by 2,841
20 more
  1. 2022DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Stepscited by 1,961
  2. 2021Structured Denoising Diffusion Models in Discrete State-Spacescited by 1,665
  3. 2022Diffusion-LM Improves Controllable Text Generationcited by 1,006
  4. 2021Score-based Generative Modeling in Latent Spacecited by 634
  5. 2023AudioLDM: Text-to-Audio Generation with Latent Diffusion Modelscited by 592
  6. 2022Fast Sampling of Diffusion Models with Exponential Integratorcited by 526
  7. 2021Diffusion Autoencoders: Toward a Meaningful and Decodable Representationcited by 447
  8. 2017PixelCNN++: Improving the PixelCNN with Discretized Logistic Mixture Likelihood and Other Modificationscited by 415
  9. 2022Analog Bits: Generating Discrete Data using Diffusion Models with Self-Conditioningcited by 362
  10. 2023Photorealistic Video Generation with Diffusion Modelscited by 304
  11. 2016Unrolled Generative Adversarial Networkscited by 208
  12. 2022Continuous diffusion for categorical datacited by 202
  13. 2022SSD-LM: Semi-autoregressive Simplex-based Diffusion Language Model for Text Generation and Modular Controlcited by 191
  14. 2023HyenaDNA: Long-Range Genomic Sequence Modeling at Single Nucleotide Resolutioncited by 187
  15. 2022Latent Diffusion for Language Generationcited by 110
  16. 2022Learning to Break the Loop: Analyzing and Mitigating Repetitions for Neural Text Generationcited by 90
  17. 2023PLANNER: Generating Diversified Paragraph via Latent Language Diffusion Modelcited by 56
  18. 2017Generating and designing DNA with deep generative modelscited by 30
  19. 2023Genomic Interpreter: A Hierarchical Genomic Deep Neural Network with 1D Shifted Window Transformercited by 2
  20. 2023Score Normalization for a Faster Diffusion Exponential Integrator Samplercited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 9; 2026: 1.

12 papers.

  1. 2024Bridging Model-Based Optimization and Generative Modeling via Conservative Fine-Tuning of Diffusion Modelscited by 24
  2. 2025CtrlDiff: Boosting Large Diffusion Language Models with Dynamic Block Prediction and Controllable Generationcited by 17
  3. 2025Regulatory DNA sequence Design with Reinforcement Learningcited by 6
  4. 2026D3LM: A Discrete DNA Diffusion Language Model for Bidirectional DNA Understanding and Generationcited by 6
  5. 2024Latent Diffusion Models for Controllable RNA Sequence Generationcited by 4
  6. 2025MergeDNA: Context-aware Genome Modeling with Dynamic Tokenization through Token Mergingcited by 2
  7. 2025Tractable Transformers for Flexible Conditional Generationcited by 1
  8. 2025Foundation Models for AI-Enabled Biological Designcited by 1
  9. 2025Language Models for Controllable DNA Sequence Designcited by 1
  10. 2025Symbolic-Diffusion: Deep Learning Based Symbolic Regression with D3PM Discrete Token Diffusioncited by 1
  11. 2025Foundations of Diffusion Models in General State Spaces: A Self-Contained Introductioncited by 1
  12. 2025Property-Isometric Variational Autoencoders for Sequence Modeling and Designcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023Latent Diffusion Model for DNA Sequence Generation
  2. 2024Absorb & Escape: Overcoming Single Model Limitations in Generating Genomic Sequences
  3. 2024TaxDiff: Taxonomic-Guided Diffusion Model for Protein Sequence Generation
  4. 2025A Unification of Discrete, Gaussian, and Simplicial Diffusion
  5. 2024Dirichlet Flow Matching with Applications to DNA Sequence Design
  6. 2023Towards Joint Sequence-Structure Generation of Nucleic Acid and Protein Complexes with SE(3)-Discrete Diffusion
  7. 2024Unlocking Guidance for Discrete State-Space Diffusion and Flow Models
  8. 2024Sifting through the Noise: A Survey of Diffusion Probabilistic Models and Their Applications to Biomolecules