mlsanityData to 7 Oct 2026

Uncertainty Estimation for Molecular Diffusion Models

arXiv 2606.13451 ↗First posted 11 Jun 2026cs.LGcited by 0

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

Abstract (arXiv)

Diffusion models have seen wide adoption for 3D molecular generation, yet they offer no principled signal of when a generated molecule is likely to be of low quality. We propose a post-hoc method for estimating per-sample uncertainty in pretrained molecular diffusion models. Building on a Laplace approximation of the denoising network, we measure the variability of the noise prediction across the generation trajectory. Empirically, we show that the resulting uncertainty score is informative of sample quality, exhibiting a negative correlation with established sample-level quality metrics. We further study how the proposed uncertainty score can be used to filter generated samples, improving model performance via test-time scaling.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Flow matching, time series and science, one of 14 directions in Diffusion models. Builds on 23 of its 25 references that are in the map. First posted on arXiv 11 Jun 2026.

Builds on

23 of 25 references.

Closest ancestors · 4

Same direction, newest first

  1. 2025Equivariant Neural Diffusion for Molecule Generation12 Jun
  2. 2023Geometric Latent Diffusion Models for 3D Molecule Generation2 May
  3. 2023Geometry-Complete Diffusion for 3D Molecule Generation and Optimization8 Feb
  4. 2022Equivariant Diffusion for Molecule Generation in 3D31 Mar

Other references · 19

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2020Denoising Diffusion Implicit Modelscited by 9,655
  3. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  4. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  5. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  6. 2022Elucidating the Design Space of Diffusion-Based Generative Modelscited by 2,994
  7. 2021Variational Diffusion Modelscited by 1,145
  8. 2018Do Deep Generative Models Know What They Don't Know?cited by 443
  9. 2021Laplace Redux -- Effortless Bayesian Deep Learningcited by 359
  10. 2015A note on the evaluation of generative modelscited by 291
  11. 2020GEOM: Energy-annotated molecular conformations for property prediction and molecular generationcited by 238
  12. 2025Inference-Time Scaling for Diffusion Models beyond Scaling Denoising Stepscited by 225
7 more
  1. 2024Understanding Hallucinations in Diffusion Models through Mode Interpolationcited by 87
  2. 2023BayesDiff: Estimating Pixel-wise Uncertainty in Diffusion via Bayesian Inferencecited by 30
  3. 2024Shedding Light on Large Generative Networks: Estimating Epistemic Uncertainty in Diffusion Modelscited by 22
  4. 2025Generative Uncertainty in Diffusion Modelscited by 20
  5. 2024Diffusion Model Guided Sampling with Pixel-Wise Aleatoric Uncertainty Estimationcited by 17
  6. 2025Adaptive Inference-Time Scaling via Cyclic Diffusion Searchcited by 7
  7. 2023Identity Curvature Laplace Approximation for Improved Out-of-Distribution Detectioncited by 4

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Breaking the Bottlenecks: Scalable Diffusion Models for 3D Molecular Generation
  2. 2025Diffusion Models are Molecular Dynamics Simulators
  3. 2023The Missing U for Efficient Diffusion Models
  4. 2026Equivariant Asynchronous Diffusion: An Adaptive Denoising Schedule for Accelerated Molecular Conformation Generation
  5. 2024A survey of probabilistic generative frameworks for molecular simulations
  6. 20233D molecule generation by denoising voxel grids
  7. 2024Diffusion Models in textitDe Novo Drug Design
  8. 2024Graph Diffusion Transformers for Multi-Conditional Molecular Generation