mlsanityData to 14 Oct 2026

SemlaFlow -- Efficient 3D Molecular Generation with Latent Attention and Equivariant Flow Matching

arXiv 2406.07266 ↗First posted 11 Jun 2024cs.LG cs.AI cs.NEcited by 41

Not on the map. Why?

Abstract (arXiv)

Methods for jointly generating molecular graphs along with their 3D conformations have gained prominence recently due to their potential impact on structure-based drug design. Current approaches, however, often suffer from very slow sampling times or generate molecules with poor chemical validity. Addressing these limitations, we propose Semla, a scalable E(3)-equivariant message passing architecture. We further introduce an unconditional 3D molecular generation model, SemlaFlow, which is trained using equivariant flow matching to generate a joint distribution over atom types, coordinates, bond types and formal charges. Our model produces state-of-the-art results on benchmark datasets with as few as 20 sampling steps, corresponding to a two order-of-magnitude speedup compared to state-of-the-art. Furthermore, we highlight limitations of current evaluation methods for 3D generation and propose new benchmark metrics for unconditional molecular generators. Finally, using these new metrics, we compare our model's ability to generate high quality samples against current approaches and further demonstrate SemlaFlow's strong performance.

Key facts. Cited by 41 papers in the map (data through 14 Oct 2026). Builds on 43 of its 59 references that are in the map. First posted on arXiv 11 Jun 2024.

Builds on

43 of 59 references.

References · 43

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  3. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  4. 2017Graph Attention Networkscited by 8,923
  5. 2022Flow Matching for Generative Modelingcited by 5,702
  6. 2016Layer Normalizationcited by 5,669
  7. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,700
  8. 2020Point Transformercited by 1,470
  9. 2022Building Normalizing Flows with Stochastic Interpolantscited by 995
  10. 2021E(n) Equivariant Graph Neural Networkscited by 965
  11. 2017Sigmoid-Weighted Linear Units for Neural Network Function Approximation in Reinforcement Learningcited by 950
  12. 2023Stochastic Interpolants: A Unifying Framework for Flows and Diffusionscited by 939
31 more
  1. 2023Improving and generalizing flow-based generative models with minibatch optimal transportcited by 879
  2. 2019On the Convergence of Adam and Beyondcited by 841
  3. 2021How Attentive are Graph Attention Networks?cited by 835
  4. 2022Equivariant Diffusion for Molecule Generation in 3Dcited by 677
  5. 2022GeoDiff: a Geometric Diffusion Model for Molecular Conformation Generationcited by 516
  6. 2022Analog Bits: Generating Discrete Data using Diffusion Models with Self-Conditioningcited by 373
  7. 2024Generative Flows on Discrete State-Spaces: Enabling Multimodal Flows with Applications to Protein Co-Designcited by 305
  8. 2022Equiformer: Equivariant Graph Attention Transformer for 3D Atomistic Graphscited by 264
  9. 2020Equivariant Flows: Exact Likelihood Generative Learning for Symmetric Densitiescited by 250
  10. 2020GEOM: Energy-annotated molecular conformations for property prediction and molecular generationcited by 243
  11. 2022Structure-based Drug Design with Equivariant Diffusion Modelscited by 217
  12. 2023Geometric Latent Diffusion Models for 3D Molecule Generationcited by 186
  13. 2022Pocket2Mol: Efficient Molecular Sampling Based on 3D Protein Pocketscited by 183
  14. 20233D Equivariant Diffusion for Target-Aware Molecule Generation and Affinity Predictioncited by 177
  15. 2021E(n) Equivariant Normalizing Flowscited by 165
  16. 2023SE(3)-Stochastic Flow Matching for Protein Backbone Generationcited by 150
  17. 2024Dirichlet Flow Matching with Applications to DNA Sequence Designcited by 115
  18. 2022Generating 3D Molecules for Target Protein Bindingcited by 104
  19. 2023MiDi: Mixed Graph and 3D Denoising Diffusion for Molecule Generationcited by 98
  20. 2023Equivariant Flow Matching with Hybrid Probability Transportcited by 60
  21. 2024Mixed Continuous and Categorical Flow Matching for 3D De Novo Molecule Generationcited by 54
  22. 2023Navigating the Design Space of Equivariant Diffusion-Based Generative Models for De Novo 3D Molecule Generationcited by 50
  23. 2023MUDiff: Unified Diffusion for Complete Molecule Generationcited by 42
  24. 2023Geometry-Complete Diffusion for 3D Molecule Generation and Optimizationcited by 37
  25. 2021Top-N: Equivariant set and graph generation without exchangeabilitycited by 36
  26. 2023Harmonic Self-Conditioned Flow Matching for Multi-Ligand Docking and Binding Site Designcited by 30
  27. 2024PILOT: Equivariant diffusion for pocket conditioned de novo ligand generation with multi-objective guidance via importance samplingcited by 19
  28. 2023AbODE: Ab Initio Antibody Design using Conjoined ODEscited by 15
  29. 2023Sample Complexity Bounds for Estimating Probability Divergences under Invariancescited by 12
  30. 2024Geometric-Facilitated Denoising Diffusion Model for 3D Molecule Generationcited by 12
  31. 2024GNN-VPA: A Variance-Preserving Aggregation Strategy for Graph Neural Networkscited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 3; 2025: 13; 2026: 25.

41 papers.

Sort:

By area:

  1. 2025All-atom Diffusion Transformers: Unified generative modelling of molecules and materialscited by 75
  2. 2025FLOWR: Flow Matching for Structure-Aware De Novo, Interaction- and Fragment-Based Ligand Generationcited by 18
  3. 2025TABASCO: A Fast, Simplified Model for Molecular Generation with Improved Physical Qualitycited by 12
  4. 2024Exploring Discrete Flow Matching for 3D De Novo Molecule Generationcited by 11
  5. 2025Transferable Generative Models Bridge Femtosecond to Nanosecond Time-Step Molecular Dynamicscited by 11
  6. 2024Flow Matching for Accelerated Simulation of Atomic Transport in Crystalline Materialscited by 9
  7. 2025GEOM-Drugs Revisited: Toward More Chemically Accurate Benchmarks for 3D Molecule Generationcited by 8
  8. 2026Rethinking Diffusion Models with Symmetries through Canonicalization with Applications to Molecular Graph Generationcited by 7
  9. 2025SynCoGen: Synthesizable 3D Molecule Generation via Joint Reaction and Coordinate Modelingcited by 5
  10. 2026Zatom-1: Towards a Multimodal Foundation Model for 3D Molecules and Materialscited by 5
  11. 2024EquiFlow: Equivariant Conditional Flow Matching with Optimal Transport for 3D Molecular Conformation Predictioncited by 3
  12. 2025NEAT: Neighborhood-Guided, Efficient, Autoregressive Set Transformer for 3D Molecular Generationcited by 3
29 more
  1. 20263D Molecule Generation from Rigid Motifs via SE(3) Flowscited by 3
  2. 2026Fast Organic Crystal Structure Prediction with Unit Cell Flow Matchingcited by 3
  3. 2025Predictive Feature Caching for Training-free Acceleration of Molecular Geometry Generationcited by 2
  4. 2025FlexiFlow: decomposable flow matching for generation of flexible molecular ensemblecited by 2
  5. 2026Permutation-Symmetrized Diffusion for Unconditional Molecular Generationcited by 2
  6. 2026Generative Molecular Morphing for Flexible-Size Design via Unbalanced Optimal Transportcited by 2
  7. 2026Boltzmann-Expected Molecular Design with Decoupled Annealing Flowscited by 2
  8. 2025Minimum-Excess-Work Guidancecited by 1
  9. 2025GAGA: Gaussianity-Aware Gaussian Approximation for Efficient 3D Molecular Generationcited by 1
  10. 2025MolSculpt: Sculpting 3D Molecular Geometries from Chemical Syntaxcited by 1
  11. 2026FlashMol: High-Quality Molecule Generation in as Few as Four Stepscited by 1
  12. 2026Toward Better Geometric Representations for Molecule Generative Modelscited by 1
  13. 2026AtomComposer: Discovering Chemical Space from First Principles with Reinforcement Learningcited by 1
  14. 2026DiverseDiT++: Quantifying, Analyzing, and Promoting Representation Diversity in Diffusion Transformerscited by 1
  15. 2025VEDA: 3D Molecular Generation via Variance-Exploding Diffusion with Annealingcited by 0
  16. 2026Hierarchy-Guided Topology Latent Flow for Molecular Graph Generationcited by 0
  17. 2026QT-Net: Rethinking Evaluation of AI Models in Atomic Chemical Spacecited by 0
  18. 2026Generating Physically Consistent Molecules with Energy-Based Modelscited by 0
  19. 2026Riemannian Diffusion Models on General Manifolds via Physics-Informed Neural Networkscited by 0
  20. 2026Sesame: Structure-Aware Molecular Generation via Spatial Density-Map Conditioningcited by 0
  21. 2026SynLaD: Latent Diffusion for Generating Synthesizable Molecules Conditioned on 3D Pharmacophore Profilescited by 0
  22. 2026DBMol: Design of High-Affinity, Target-Specific Small Molecules through Structure Prediction Modelscited by 0
  23. 2026PocketVE: Stable and Property-Guided Structure-Based Drug Design with Variance-Exploding Diffusioncited by 0
  24. 2026A Systematic Evaluation of Molecule Generation Models for De Novo Drug Design: From Benchmarks to Practical Insightscited by 0
  25. 2026Ensemble-Conditioned Molecular Designcited by 0
  26. 2026TreeRef-BFN: Equivariance-Free De Novo Molecule Generation based on 2D Topology and Internal 3D Geometrycited by 0
  27. 2026GLASS: Global Latent Aggregation with Slot-based Set Decoding for Scalable All-Atom Crystal Generationcited by 0
  28. 2026Autoregressive Frontier Expansion: Growing Trees with Graph Machine Learningcited by 0
  29. 2026OctMole: Multiscale 3D Molecular Generation with Hierarchical Spatial Flowscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025FlowMol3: Flow Matching for 3D De Novo Small-Molecule Generation
  2. 2026Fixed-Dimensional Latent Flow for Generating Variable-Size 3D Molecules
  3. 2023Coarse-to-Fine: a Hierarchical Diffusion Model for Molecule Generation in 3D
  4. 2025Applications of Modular Co-Design for De Novo 3D Molecule Generation
  5. 2025Energy-Based Flow Matching for Generating 3D Molecular Structure
  6. 2025Efficient Molecular Conformer Generation with SO(3)-Averaged Flow Matching and Reflow
  7. 2025D3MES: Diffusion Transformer with multihead equivariant self-attention for 3D molecule generation
  8. 2022MDM: Molecular Diffusion Model for 3D Molecule Generation