mlsanityData to 13 Oct 2026

3D Molecule Generation from Rigid Motifs via SE(3) Flows

arXiv 2601.16955 ↗First posted 23 Jan 2026cs.LGcited by 3

Not on the map. Why?

Abstract (arXiv)

Three-dimensional molecular structure generation is typically performed at the level of individual atoms, yet molecular graph generation techniques often consider fragments as their structural units. Building on the advances in frame-based protein structure generation, we extend these fragmentation ideas to 3D, treating general molecules as sets of rigid-body motifs. Utilising this representation, we employ SE(3)-equivariant generative modelling for de novo 3D molecule generation from rigid motifs. In our evaluations, we observe comparable or superior results to state-of-the-art across benchmarks, surpassing it in atom stability on GEOM-Drugs, while yielding a 2x to 10x reduction in generation steps and offering 3.5x compression in molecular representations compared to the standard atom-based methods.

Key facts. Cited by 3 papers in the map (data through 13 Oct 2026). Builds on 37 of its 52 references that are in the map. First posted on arXiv 23 Jan 2026.

Builds on

37 of 52 references.

References · 37

  1. 2022Flow Matching for Generative Modelingcited by 5,542
  2. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,607
  3. 2022Building Normalizing Flows with Stochastic Interpolantscited by 979
  4. 2021E(n) Equivariant Graph Neural Networkscited by 957
  5. 2023Improving and generalizing flow-based generative models with minibatch optimal transportcited by 857
  6. 2022Equivariant Diffusion for Molecule Generation in 3Dcited by 672
  7. 2018Junction Tree Variational Autoencoder for Molecular Graph Generationcited by 648
  8. 2022GeoDiff: a Geometric Diffusion Model for Molecular Conformation Generationcited by 514
  9. 2022Analog Bits: Generating Discrete Data using Diffusion Models with Self-Conditioningcited by 365
  10. 2024Generative Flows on Discrete State-Spaces: Enabling Multimodal Flows with Applications to Protein Co-Designcited by 299
  11. 2023Flow Matching on General Geometriescited by 262
  12. 2020GEOM: Energy-annotated molecular conformations for property prediction and molecular generationcited by 238
25 more
  1. 2023SE(3) diffusion model with application to protein backbone generationcited by 218
  2. 2020Hierarchical Generation of Molecular Graphs using Structural Motifscited by 204
  3. 2023Geometric Latent Diffusion Models for 3D Molecule Generationcited by 185
  4. 2021E(n) Equivariant Normalizing Flowscited by 165
  5. 2023SE(3)-Stochastic Flow Matching for Protein Backbone Generationcited by 148
  6. 2022Equivariant 3D-Conditional Diffusion Models for Molecular Linker Designcited by 121
  7. 2022Diffusion-based Molecule Generation with Informative Prior Bridgescited by 105
  8. 2021Inverse design of 3d molecular structures with conditional generative neural networkscited by 93
  9. 2024Variational Flow Matching for Graph Generationcited by 82
  10. 2022Equivariant Energy-Guided SDE for Inverse Molecular Designcited by 73
  11. 2021Learning to Extend Molecular Scaffolds with Structural Motifscited by 70
  12. 2024Fisher Flow Matching for Generative Modeling over Discrete Datacited by 70
  13. 2023MolDiff: Addressing the Atom-Bond Inconsistency Problem in 3D Molecule Diffusion Generationcited by 65
  14. 2023Bayesian Flow Networkscited by 63
  15. 2023Equivariant Flow Matching with Hybrid Probability Transportcited by 59
  16. 2024Mixed Continuous and Categorical Flow Matching for 3D De Novo Molecule Generationcited by 54
  17. 2021Molecule Generation by Principal Subgraph Mining and Assemblingcited by 53
  18. 2023De Novo Molecular Generation via Connection-aware Motif Miningcited by 45
  19. 2024SemlaFlow -- Efficient 3D Molecular Generation with Latent Attention and Equivariant Flow Matchingcited by 40
  20. 20233D molecule generation by denoising voxel gridscited by 38
  21. 2023Harmonic Self-Conditioned Flow Matching for Multi-Ligand Docking and Binding Site Designcited by 30
  22. 2023Coarse-to-Fine: a Hierarchical Diffusion Model for Molecule Generation in 3Dcited by 24
  23. 2025Applications of Modular Co-Design for De Novo 3D Molecule Generationcited by 13
  24. 2025Equivariant Neural Diffusion for Molecule Generationcited by 13
  25. 2025FragFM: Hierarchical Framework for Efficient Molecule Generation via Fragment-Level Discrete Flow Matchingcited by 5

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026FragmentFlow: Scalable Transition State Generation for Large Moleculescited by 2
  2. 2026Generative Molecular Morphing for Flexible-Size Design via Unbalanced Optimal Transportcited by 2
  3. 2026Toward Better Geometric Representations for Molecule Generative Modelscited by 1