mlsanityData to 7 Oct 2026

Adaptive Moments are Surprisingly Effective for Plug-and-Play Diffusion Sampling

arXiv 2603.16797 ↗First posted 17 Mar 2026cs.LG cs.CVcited by 0

On the map: Diffusion models → Inverse problems and image restoration

Abstract (arXiv)

Guided diffusion sampling relies on approximating often intractable likelihood scores, which introduces significant noise into the sampling dynamics. We propose using adaptive moment estimation to stabilize these noisy likelihood scores during sampling. Despite its simplicity, our approach achieves state-of-the-art results on image restoration and class-conditional generation tasks, outperforming more complicated methods, which are often computationally more expensive. We provide empirical analysis of our method on both synthetic and real data, demonstrating that mitigating gradient noise through adaptive moments offers an effective way to improve alignment.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Inverse problems and image restoration, one of 14 directions in Diffusion models. Builds on 33 of its 45 references that are in the map. First posted on arXiv 17 Mar 2026.

Builds on

33 of 45 references.

Closest ancestors · 4

Same direction, newest first

  1. 2023A Variational Perspective on Solving Inverse Problems with Diffusion Models7 May
  2. 2022Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Model1 Dec
  3. 2022Diffusion Posterior Sampling for General Noisy Inverse Problems29 Sep
  4. 2022Denoising Diffusion Restoration Models27 Jan

Other references · 29

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  4. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  5. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  6. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  7. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,539
  8. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
  9. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  10. 2022Elucidating the Design Space of Diffusion-Based Generative Modelscited by 2,994
  11. 2022Video Diffusion Modelscited by 2,280
  12. 2021Image Super-Resolution via Iterative Refinementcited by 1,506
17 more
  1. 2022RePaint: Inpainting using Denoising Diffusion Probabilistic Modelscited by 1,419
  2. 2020DiffWave: A Versatile Diffusion Model for Audio Synthesiscited by 1,339
  3. 2022Null-text Inversion for Editing Real Images using Guided Diffusion Modelscited by 1,168
  4. 2021Variational Diffusion Modelscited by 1,145
  5. 2024WorldSimBench: Towards Video Generation Models as World Simulatorscited by 867
  6. 2022Equivariant Diffusion for Molecule Generation in 3Dcited by 666
  7. 2023AudioLDM: Text-to-Audio Generation with Latent Diffusion Modelscited by 592
  8. 2023Universal Guidance for Diffusion Modelscited by 426
  9. 2023Rethinking FID: Towards a Better Evaluation Metric for Image Generationcited by 303
  10. 2023Understanding Diffusion Objectives as the ELBO with Simple Data Augmentationcited by 293
  11. 2023FreeDoM: Training-Free Energy-Guided Conditional Diffusion Modelcited by 290
  12. 2023Reduce, Reuse, Recycle: Compositional Generation with Energy-Based Diffusion Models and MCMCcited by 216
  13. 2023Manifold Preserving Guided Diffusioncited by 153
  14. 2023Unexpected Improvements to Expected Improvement for Bayesian Optimizationcited by 144
  15. 2024TFG: Unified Training-Free Guidance for Diffusion Modelscited by 103
  16. 2024Free Hunch: Denoiser Covariance Estimation for Diffusion Models Without Extra Costscited by 14
  17. 2026Physics-informed diffusion models in spectral spacecited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Diffusion Posterior Proximal Sampling for Image Restoration
  2. 2024Multistep Distillation of Diffusion Models via Moment Matching
  3. 2024A Simple Early Exiting Framework for Accelerated Sampling in Diffusion Models
  4. 2026Couple to Control: Joint Initial Noise Design in Diffusion Models
  5. 2024Enhancing Diffusion Posterior Sampling for Inverse Problems by Integrating Crafted Measurements
  6. 2025Ctrl-Z Sampling: Scaling Diffusion Sampling with Controlled Random Zigzag Explorations
  7. 2024Diffusion Priors for Variational Likelihood Estimation and Image Denoising
  8. 2025Sampling-Aware Quantization for Diffusion Models