mlsanityData to 14 Oct 2026

Straight-Line Diffusion Model for Efficient 3D Molecular Generation

arXiv 2503.02918 ↗First posted 4 Mar 2025cs.LG cs.AIcited by 8

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

Abstract (arXiv)

Diffusion-based models have shown great promise in molecular generation but often require a large number of sampling steps to generate valid samples. In this paper, we introduce a novel Straight-Line Diffusion Model (SLDM) to tackle this problem, by formulating the diffusion process to follow a linear trajectory. The proposed process aligns well with the noise sensitivity characteristic of molecular structures and uniformly distributes reconstruction effort across the generative process, thus enhancing learning efficiency and efficacy. Consequently, SLDM achieves state-of-the-art performance on 3D molecule generation benchmarks, delivering a 100-fold improvement in sampling efficiency.

Key facts. Cited by 8 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 44 of its 57 references that are in the map. First posted on arXiv 4 Mar 2025.

Builds on

44 of 57 references.

Closest ancestors · 12

Same direction, newest first

  1. 2024Optimal Flow Matching: Learning Straight Trajectories in Just One Step19 Mar
  2. 2023Navigating the Design Space of Equivariant Diffusion-Based Generative Models for De Novo 3D Molecule Generation29 Sep
  3. 2023Bayesian Flow Networks14 Aug
  4. 2023Learning Joint 2D & 3D Diffusion Models for Complete Molecule Generation21 May
  5. 2023Geometric Latent Diffusion Models for 3D Molecule Generation2 May
  6. 2023MiDi: Mixed Graph and 3D Denoising Diffusion for Molecule Generation17 Feb
  7. 2023Improving and generalizing flow-based generative models with minibatch optimal transport1 Feb
  8. 2022Flow Matching for Generative Modeling6 Oct
  9. 2022MDM: Molecular Diffusion Model for 3D Molecule Generation13 Sep
  10. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow7 Sep
  11. 2022Equivariant Diffusion for Molecule Generation in 3D31 Mar
  12. 2022GeoDiff: a Geometric Diffusion Model for Molecular Conformation Generation6 Mar

Other references · 32

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  3. 2020Denoising Diffusion Implicit Modelscited by 9,781
  4. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  5. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  6. 2022Scalable Diffusion Models with Transformerscited by 6,054
  7. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,101
  8. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,761
  9. 2022Elucidating the Design Space of Diffusion-Based Generative Modelscited by 3,045
  10. 2022DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Stepscited by 1,979
  11. 2023Consistency Modelscited by 1,822
  12. 2021E(n) Equivariant Graph Neural Networkscited by 965
20 more
  1. 2023Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inferencecited by 846
  2. 2022Sampling is as easy as learning the score: theory for diffusion models with minimal data assumptionscited by 445
  3. 2020Equivariant Flows: Exact Likelihood Generative Learning for Symmetric Densitiescited by 250
  4. 2020GEOM: Energy-annotated molecular conformations for property prediction and molecular generationcited by 243
  5. 2019Symmetry-adapted generation of 3d point sets for the targeted discovery of moleculescited by 172
  6. 2021E(n) Equivariant Normalizing Flowscited by 165
  7. 2022Diffusion-based Molecule Generation with Informative Prior Bridgescited by 106
  8. 2023SA-Solver: Stochastic Adams Solver for Fast Sampling of Diffusion Modelscited by 72
  9. 2023AutoDiffusion: Training-Free Optimization of Time Steps and Architectures for Automated Diffusion Model Accelerationcited by 70
  10. 2024Accelerating Diffusion Sampling with Optimized Time Stepscited by 67
  11. 2023MolDiff: Addressing the Atom-Bond Inconsistency Problem in 3D Molecule Diffusion Generationcited by 65
  12. 2024Neural Flow Diffusion Models: Learnable Forward Process for Improved Diffusion Modellingcited by 45
  13. 2023MUDiff: Unified Diffusion for Complete Molecule Generationcited by 42
  14. 2024Unifying Bayesian Flow Networks and Diffusion Models through Stochastic Differential Equationscited by 28
  15. 2017Continuous-Time Flows for Efficient Inference and Density Estimationcited by 21
  16. 2024UniGEM: A Unified Approach to Generation and Property Prediction for Moleculescited by 21
  17. 2023Symphony: Symmetry-Equivariant Point-Centered Spherical Harmonics for 3D Molecule Generationcited by 17
  18. 2024Geometric Representation Condition Improves Equivariant Molecule Generationcited by 13
  19. 2024Generating Physical Dynamics under Priorscited by 6
  20. 2024Diffusion Twigs with Loop Guidance for Conditional Graph Generationcited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 5; 2026: 3.

8 papers.

  1. 2025PartRM: Modeling Part-Level Dynamics with Large Cross-State Reconstruction Modelcited by 15
  2. 2025FB-4D: Spatial-Temporal Coherent Dynamic 3D Content Generation with Feature Bankscited by 3
  3. 2025Predictive Feature Caching for Training-free Acceleration of Molecular Geometry Generationcited by 2
  4. 2025GAGA: Gaussianity-Aware Gaussian Approximation for Efficient 3D Molecular Generationcited by 1
  5. 2025MolPIF: A Parameter Interpolation Flow Model for Molecule Generationcited by 1
  6. 2026FlashMol: High-Quality Molecule Generation in as Few as Four Stepscited by 1
  7. 2026EvoEGF-Mol: Evolving Exponential Geodesic Flow for Structure-based Drug Designcited by 0
  8. 2026Generating Physically Consistent Molecules with Energy-Based Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Breaking the Bottlenecks: Scalable Diffusion Models for 3D Molecular Generation
  2. 2024Diffusion Models in textitDe Novo Drug Design
  3. 2024Geometric-Facilitated Denoising Diffusion Model for 3D Molecule Generation
  4. 2023Coarse-to-Fine: a Hierarchical Diffusion Model for Molecule Generation in 3D
  5. 2025D3MES: Diffusion Transformer with multihead equivariant self-attention for 3D molecule generation
  6. 2025Diffusion Models for Molecules: A Survey of Methods and Tasks
  7. 2025Unraveling the Potential of Diffusion Models in Small Molecule Generation
  8. 2026Autoregressive latent diffusion for 3D molecule generation