mlsanityData to 7 Oct 2026

Latent Target Score Matching, with an application to Simulation-Based Inference

arXiv 2602.07189 ↗First posted 6 Feb 2026cs.LGcited by 1

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

Denoising score matching (DSM) for training diffusion models may suffer from high variance at low noise levels. Target Score Matching (TSM) mitigates this when clean data scores are available, providing a low-variance objective. In many applications clean scores are inaccessible due to the presence of latent variables, leaving only joint signals exposed. We propose Latent Target Score Matching (LTSM), an extension of TSM to leverage joint scores for low-variance supervision of the marginal score. While LTSM is effective at low noise levels, a mixture with DSM ensures robustness across noise scales. Across simulation-based inference tasks, LTSM consistently improves variance, score accuracy, and sample quality.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 19 of its 32 references that are in the map. First posted on arXiv 6 Feb 2026.

Builds on

19 of 32 references.

Closest ancestors · 4

Same direction, newest first

  1. 2024Target Score Matching13 Feb
  2. 2022Elucidating the Design Space of Diffusion-Based Generative Models1 Jun
  3. 2020Score-Based Generative Modeling through Stochastic Differential Equations26 Nov
  4. 2020Denoising Diffusion Probabilistic Models19 Jun

Other references · 15

  1. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  2. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  3. 2016Variational Inference: A Review for Statisticianscited by 1,466
  4. 2019Normalizing Flows for Probabilistic Modeling and Inferencecited by 1,315
  5. 2019The frontier of simulation-based inferencecited by 490
  6. 2018Sequential Neural Likelihood: Fast Likelihood-free Inference with Autoregressive Flowscited by 217
  7. 2019Automatic Posterior Transformation for Likelihood-Free Inferencecited by 216
  8. 2017Flexible statistical inference for mechanistic models of neural dynamicscited by 162
  9. 2022Protein structure generation via folding diffusioncited by 113
  10. 2023Two for One: Diffusion Models and Force Fields for Coarse-Grained Molecular Dynamicscited by 72
  11. 2025Proteina: Scaling Flow-based Protein Structure Generative Modelscited by 63
  12. 2018Likelihood-free inference with emulator networkscited by 61
3 more
  1. 2018Mining gold from implicit models to improve likelihood-free inferencecited by 60
  2. 2022Compositional Score Modeling for Simulation-based Inferencecited by 46
  3. 2018A Likelihood-Free Inference Framework for Population Genetic Data using Exchangeable Neural Networkscited by 30

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Bridge Matching Sampler: Scalable Sampling via Generalized Fixed-Point Diffusion Matchingcited by 7

Similar, not cited

Close in wording, no citation either way

  1. 2025Heteroscedasticity of Denoising Score Matching with Generalised Smooth Noise
  2. 2024What's the score? Automated Denoising Score Matching for Nonlinear Diffusions
  3. 2025Latent Nonlinear Denoising Score Matching for Enhanced Learning of Structured Distributions
  4. 2025DDPM Score Matching and Distribution Learning
  5. 2025Denoising Score Matching with Random Features: Insights on Diffusion Models from Precise Learning Curves
  6. 2024Nonlinear denoising score matching for enhanced learning of structured distributions
  7. 2023Stable Target Field for Reduced Variance Score Estimation in Diffusion Models
  8. 2025Target Concrete Score Matching: A Holistic Framework for Discrete Diffusion