mlsanityData to 14 Oct 2026

Equivariant Neural Diffusion for Molecule Generation

arXiv 2506.10532 ↗First posted 12 Jun 2025cs.LGcited by 13

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

Abstract (arXiv)

We introduce Equivariant Neural Diffusion (END), a novel diffusion model for molecule generation in 3D that is equivariant to Euclidean transformations. Compared to current state-of-the-art equivariant diffusion models, the key innovation in END lies in its learnable forward process for enhanced generative modelling. Rather than pre-specified, the forward process is parameterized through a time- and data-dependent transformation that is equivariant to rigid transformations. Through a series of experiments on standard molecule generation benchmarks, we demonstrate the competitive performance of END compared to several strong baselines for both unconditional and conditional generation.

Key facts. Cited by 13 papers in the map (data through 14 Oct 2026). Placed in Flow matching, time series and science, one of 14 directions in Diffusion models. Builds on 38 of its 56 references that are in the map. First posted on arXiv 12 Jun 2025.

Builds on

38 of 56 references.

Closest ancestors · 12

Same direction, newest first

  1. 2024Conditional Synthesis of 3D Molecules with Time Correction Sampler1 Nov
  2. 2023Equivariant Flow Matching with Hybrid Probability Transport12 Dec
  3. 2023Navigating the Design Space of Equivariant Diffusion-Based Generative Models for De Novo 3D Molecule Generation29 Sep
  4. 2023Practical and Asymptotically Exact Conditional Sampling in Diffusion Models30 Jun
  5. 2023Coarse-to-Fine: a Hierarchical Diffusion Model for Molecule Generation in 3D5 May
  6. 2023Geometric Latent Diffusion Models for 3D Molecule Generation2 May
  7. 2023EigenFold: Generative Protein Structure Prediction with Diffusion Models5 Apr
  8. 2023MiDi: Mixed Graph and 3D Denoising Diffusion for Molecule Generation17 Feb
  9. 2022Equivariant 3D-Conditional Diffusion Models for Molecular Linker Design11 Oct
  10. 2022Flow Matching for Generative Modeling6 Oct
  11. 2022Equivariant Diffusion for Molecule Generation in 3D31 Mar
  12. 2022GeoDiff: a Geometric Diffusion Model for Molecular Conformation Generation6 Mar

Other references · 26

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  3. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  4. 2021Variational Diffusion Modelscited by 1,153
  5. 2022Diffusion Models: A Comprehensive Survey of Methods and Applicationscited by 1,114
  6. 2021E(3)-Equivariant Graph Neural Networks for Data-Efficient and Accurate Interatomic Potentialscited by 708
  7. 2017SchNet: A continuous-filter convolutional neural network for modeling quantum interactionscited by 571
  8. 2022MACE: Higher Order Equivariant Message Passing Neural Networks for Fast and Accurate Force Fieldscited by 474
  9. 2021Equivariant message passing for the prediction of tensorial properties and molecular spectracited by 441
  10. 2022Analog Bits: Generating Discrete Data using Diffusion Models with Self-Conditioningcited by 373
  11. 2020GEOM: Energy-annotated molecular conformations for property prediction and molecular generationcited by 243
  12. 2020Machine Learning Force Fieldscited by 207
14 more
  1. 2019Symmetry-adapted generation of 3d point sets for the targeted discovery of moleculescited by 172
  2. 2021E(n) Equivariant Normalizing Flowscited by 165
  3. 2022Diffusion-based Molecule Generation with Informative Prior Bridgescited by 106
  4. 2021Inverse design of 3d molecular structures with conditional generative neural networkscited by 93
  5. 2021Generating 3D Molecules Conditional on Receptor Binding Sites with Deep Generative Modelscited by 73
  6. 2022Equivariant Energy-Guided SDE for Inverse Molecular Designcited by 73
  7. 2023Timewarp: Transferable Acceleration of Molecular Dynamics by Learning Time-Coarsened Dynamicscited by 66
  8. 2023MolDiff: Addressing the Atom-Bond Inconsistency Problem in 3D Molecule Diffusion Generationcited by 65
  9. 2020Reinforcement Learning for Molecular Design Guided by Quantum Mechanicscited by 51
  10. 2024Neural Flow Diffusion Models: Learnable Forward Process for Improved Diffusion Modellingcited by 45
  11. 20233D molecule generation by denoising voxel gridscited by 40
  12. 2023Neural Diffusion Modelscited by 21
  13. 2023DiffEnc: Variational Diffusion with a Learned Encodercited by 17
  14. 2023Symphony: Symmetry-Equivariant Point-Centered Spherical Harmonics for 3D Molecule Generationcited by 17

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 4; 2026: 9.

13 papers.

Sort:

By area:

  1. 2025Controlled Generation with Equivariant Variational Flow Matchingcited by 9
  2. 2025Kinetic Langevin Diffusion for Crystalline Materials Generationcited by 9
  3. 2025Guiding Diffusion Models with Reinforcement Learning for Stable Molecule Generationcited by 4
  4. 20263D Molecule Generation from Rigid Motifs via SE(3) Flowscited by 3
  5. 2026Elign: Equivariant Diffusion Model Alignment from Foundational Machine Learning Force Fieldscited by 3
  6. 2026GEPC: Group-Equivariant Posterior Consistency for Out-of-Distribution Detection in Diffusion Modelscited by 1
  7. 2026AtomComposer: Discovering Chemical Space from First Principles with Reinforcement Learningcited by 1
  8. 2025Challenges in Non-Polymeric Crystal Structure Prediction: Why a Geometric, Permutation-Invariant Loss is Neededcited by 0
  9. 2026DEGMC: Denoising Diffusion Models Based on Riemannian Equivariant Group Morphological Convolutionscited by 0
  10. 2026Generating Physically Consistent Molecules with Energy-Based Modelscited by 0
  11. 2026Uncertainty Estimation for Molecular Diffusion Modelscited by 0
  12. 2026Renormalization Group Flow Matching for Scalable Local Generative Modelingcited by 0
1 more
  1. 2026A Systematic Evaluation of Molecule Generation Models for De Novo Drug Design: From Benchmarks to Practical Insightscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Scalable Non-Equivariant 3D Molecule Generation via Rotational Alignment
  2. 2025Frame-based Equivariant Diffusion Models for 3D Molecular Generation
  3. 2024SymDiff: Equivariant Diffusion via Stochastic Symmetrisation
  4. 2025D3MES: Diffusion Transformer with multihead equivariant self-attention for 3D molecule generation
  5. 2026Quotient-Space Diffusion Models
  6. 2026Autoregressive latent diffusion for 3D molecule generation
  7. 2022MDM: Molecular Diffusion Model for 3D Molecule Generation
  8. 2024Equivariant Blurring Diffusion for Hierarchical Molecular Conformer Generation