arXiv Machine Learning July 7, 2026 By Ron Levi, Michael Elad

Mixture-of-Gaussians-Guided Schedule Design for Brownian Bridge Diffusion Models

Read the original on arXiv Machine Learning →

arXiv:2607. 03517v1 Announce Type: new Abstract: Brownian Bridge Diffusion Models (BBDM) offer an appealing framework for image restoration and inverse problems by constructing a stochastic bridge from the clean signal directly to the degraded observation, rather than to pure noise.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv AI

1d ago

Scale-Consistent Posterior Dynamics for Diffusion Inverse Problems

arXiv:2608. 15144v1 Announce Type: cross Abstract: Posterior sampling with a pretrained diffusion prior is governed by a conditional score whose intermediate likelihood component is generally intractable.

By Zhaoqiang Liu, Tongyao Pang, Ruibing Wang, Yang Zheng

diffusion benchmarks

arXiv Machine Learning

Jun 2

Hallucination-Aware Diffusion Sampling for Inverse Problems via Robust Prior Updates

arXiv:2606. 02331v1 Announce Type: cross Abstract: Diffusion-based inverse problem solvers can produce realistic reconstructions, but realism alone does not ensure that the recovered details are supported by the measurement.

By Pengfei Jin, Yiqi Tian, Kailong Fan, Bingjie Qi, Quanzheng Li

diffusion safety

arXiv AI

Jun 18

Posterior Continuation with Noise-Conditioned Frequency Exposure for Diffusion Inverse Problems

arXiv:2602. 00176v2 Announce Type: replace-cross Abstract: Diffusion posterior sampling solves inverse problems by combining a pretrained diffusion prior with measurement-consistency guidance.

By Feng Tian, Yixuan Li, Weili Zeng, Weitian Zhang, Yichao Yan, Xiaokang Yang

diffusion benchmarks

arXiv Machine Learning

Jul 28

Exact Evaluation of the Accuracy of Diffusion Models for Inverse Problems with Gaussian Data Distributions

arXiv:2507. 07008v2 Announce Type: replace Abstract: Used as priors for Bayesian inverse problems, diffusion models have recently attracted considerable attention in the literature.

By Emile Pierret, Bruno Galerne

diffusion

arXiv Machine Learning

Jun 3

RMPrior: Bridging Propagation Priors and Diffusion Refinement for Efficient Radio Map Construction

arXiv:2606. 03074v1 Announce Type: new Abstract: Diffusion models achieve high-fidelity radio map construction through iterative denoising, yet their sampling cost limits practicality in dynamic wireless systems where radio maps must be refreshed repeatedly.

By Zixuan Guo, Xiucheng Wang, Nan Cheng

diffusion benchmarks

arXiv AI

Aug 11

SDDBMs: Soft Denoising Diffusion Bridge Models

arXiv:2608. 08594v1 Announce Type: new Abstract: Diffusion bridge models leverage Doob's \(h\)-transform to construct stochastic transports between arbitrary endpoint distributions, and have shown strong potential in image-to-image translation and restoration.

By Shiyi Qi, Kun He, Mingmou Liu

diffusion

Related stories

Scale-Consistent Posterior Dynamics for Diffusion Inverse Problems

Hallucination-Aware Diffusion Sampling for Inverse Problems via Robust Prior Updates

Posterior Continuation with Noise-Conditioned Frequency Exposure for Diffusion Inverse Problems

Exact Evaluation of the Accuracy of Diffusion Models for Inverse Problems with Gaussian Data Distributions

RMPrior: Bridging Propagation Priors and Diffusion Refinement for Efficient Radio Map Construction

SDDBMs: Soft Denoising Diffusion Bridge Models