mlsanityData to 14 Oct 2026

Flow-Matching Based Refiner for Molecular Conformer Generation

arXiv 2510.04878 ↗First posted 6 Oct 2025cs.LG q-bio.QMcited by 1

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

Abstract (arXiv)

Low-energy molecular conformers generation (MCG) is a foundational yet challenging problem in drug discovery. Denoising-based methods include diffusion and flow-matching methods that learn mappings from a simple base distribution to the molecular conformer distribution. However, these approaches often suffer from error accumulation during sampling, especially in the low SNR steps, which are hard to train. To address these challenges, we propose a flow-matching refiner for the MCG task. The proposed method initializes sampling from mixed-quality outputs produced by upstream denoising models and reschedules the noise scale to bypass the low-SNR phase, thereby improving sample quality. On the GEOM-QM9 and GEOM-Drugs benchmark datasets, the generator-refiner pipeline improves quality with fewer total denoising steps while preserving diversity.

Key facts. Cited by 1 paper 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 32 of its 43 references that are in the map. First posted on arXiv 6 Oct 2025.

Builds on

32 of 43 references.

Closest ancestors · 7

Same direction, newest first

  1. 2025NExT-Mol: 3D Diffusion Meets 1D Language Modeling for 3D Molecule Generation18 Feb
  2. 2023Swallowing the Bitter Pill: Simplified Scalable Conformer Generation27 Nov
  3. 2023Multisample Flow Matching: Straightening Flows with Minibatch Couplings28 Apr
  4. 2023Improving and generalizing flow-based generative models with minibatch optimal transport1 Feb
  5. 2022Flow Matching for Generative Modeling6 Oct
  6. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow7 Sep
  7. 2022GeoDiff: a Geometric Diffusion Model for Molecular Conformation Generation6 Mar

Other references · 25

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  3. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,356
  4. 2022Elucidating the Design Space of Diffusion-Based Generative Modelscited by 3,045
  5. 2021Image Super-Resolution via Iterative Refinementcited by 1,511
  6. 2022Building Normalizing Flows with Stochastic Interpolantscited by 995
  7. 2022Denoising Diffusion Restoration Modelscited by 963
  8. 2023Stochastic Interpolants: A Unifying Framework for Flows and Diffusionscited by 939
  9. 2024SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformerscited by 737
  10. 2024Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Thinkcited by 703
  11. 2020Directional Message Passing for Molecular Graphscited by 561
  12. 2022Improving Diffusion Models for Inverse Problems using Manifold Constraintscited by 508
13 more
  1. 2021Equivariant message passing for the prediction of tensorial properties and molecular spectracited by 441
  2. 2023Q-Diffusion: Quantizing Diffusion Modelscited by 273
  3. 2022Torsional Diffusion for Molecular Conformer Generationcited by 263
  4. 2021Deblurring via Stochastic Refinementcited by 249
  5. 2020GEOM: Energy-annotated molecular conformations for property prediction and molecular generationcited by 243
  6. 2021Learning Gradient Fields for Molecular Conformation Generationcited by 163
  7. 2021GeoMol: Torsional Geometric Generation of Molecular 3D Conformer Ensemblescited by 107
  8. 2022DiffuseVAE: Efficient, Controllable and High-Fidelity Generation from Low-Dimensional Latentscited by 104
  9. 2024ET-Flow: Equivariant Flow-Matching for Molecular Conformer Generationcited by 43
  10. 2024Improved Noise Schedule for Diffusion Trainingcited by 39
  11. 2023On Error Propagation of Diffusion Modelscited by 31
  12. 2020Molecular machine learning with conformer ensemblescited by 27
  13. 2022Diffiner: A Versatile Diffusion-based Generative Refiner for Speech Enhancementcited by 14

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Rethinking Refinement: Correcting Generative Bias without Noise Injectioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Efficient Molecular Conformer Generation with SO(3)-Averaged Flow Matching and Reflow
  2. 2025FlexiFlow: decomposable flow matching for generation of flexible molecular ensemble
  3. 2025Energy-Based Flow Matching for Generating 3D Molecular Structure
  4. 2026Flow Sampling: Learning to Sample from Unnormalized Densities via Denoising Conditional Processes
  5. 2026Geometric Flow Matching for Molecular Conformation Generation via Manifold Decomposition
  6. 2026Breaking the Bottlenecks: Scalable Diffusion Models for 3D Molecular Generation
  7. 2025FlowMol3: Flow Matching for 3D De Novo Small-Molecule Generation
  8. 2026Equivariant Asynchronous Diffusion: An Adaptive Denoising Schedule for Accelerated Molecular Conformation Generation