mlsanityData to 14 Oct 2026

Generative diffusion posterior sampling for informative likelihoods

arXiv 2506.01083 ↗First posted 1 Jun 2025stat.ML cs.LG cs.SYcited by 4

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

Sequential Monte Carlo (SMC) methods have recently shown successful results for conditional sampling of generative diffusion models. In this paper we propose a new diffusion posterior SMC sampler achieving improved statistical efficiencies, particularly under outlier conditions or highly informative likelihoods. The key idea is to construct an observation path that correlates with the diffusion model and to design the sampler to leverage this correlation for more efficient sampling. Empirical results conclude the efficiency.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 16 of its 22 references that are in the map. First posted on arXiv 1 Jun 2025.

Builds on

16 of 22 references.

Closest ancestors · 6

Same direction, newest first

  1. 2024Conditional sampling within generative diffusion models15 Sep
  2. 2024Conditioning diffusion models by explicit forward-backward bridging22 May
  3. 2022From Denoising Diffusions to Denoising Markov Models7 Nov
  4. 2021Diffusion Schr"odinger Bridge with Applications to Score-Based Generative Modeling1 Jun
  5. 2020Score-Based Generative Modeling through Stochastic Differential Equations26 Nov
  6. 2020Denoising Diffusion Probabilistic Models19 Jun

Other references · 10

  1. 2022Diffusion Posterior Sampling for General Noisy Inverse Problemscited by 1,416
  2. 2023Stochastic Interpolants: A Unifying Framework for Flows and Diffusionscited by 939
  3. 2022Diffusion probabilistic modeling of protein backbones in 3D for the motif-scaffolding problemcited by 236
  4. 2023Practical and Asymptotically Exact Conditional Sampling in Diffusion Modelscited by 232
  5. 2023Image Restoration with Mean-Reverting Stochastic Differential Equationscited by 183
  6. 2024A Survey on Diffusion Models for Inverse Problemscited by 180
  7. 2024Divide-and-Conquer Posterior Sampling for Denoising Diffusion Priorscited by 28
  8. 2024Taming Diffusion Models for Image Restoration: A Reviewcited by 12
  9. 2025Solving Linear-Gaussian Bayesian Inverse Problems with Decoupled Diffusion Sequential Monte Carlocited by 10
  10. 2025Reverse Markov Learning: Multi-Step Generative Models for Complex Distributionscited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 2.

4 papers.

  1. 2025Efficient Zero-Shot Inpainting with Decoupled Diffusion Guidancecited by 5
  2. 2026Particle-Guided Diffusion Models for Partial Differential Equationscited by 5
  3. 2025Diffusion differentiable resamplingcited by 2
  4. 2026Particle-Guided Diffusion for Gas-Phase Reaction Kineticscited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2026Non-Asymptotic Error Bounds for SMC with Biased Proposals: Application to Conditional Diffusion Sampling
  2. 2025Inverse Problem Sampling in Latent Space Using Sequential Monte Carlo
  3. 2025Information-Theoretic Proofs for Diffusion Sampling
  4. 2025Briding Diffusion Posterior Sampling and Monte Carlo methods: a survey
  5. 2025Generative Uncertainty in Diffusion Models
  6. 2025Generative Modeling with Bayesian Sample Inference
  7. 2026Leveraging generative models to assist Monte Carlo sampling
  8. 2026Multilevel and Sequential Monte Carlo for Training-Free Diffusion Guidance