FlowSGS introduces a flow-based posterior sampling method that combines Split Gibbs Sampling (SGS) with Langevin dynamics for the likelihood step and Stochastic Interpolants (SI) for the prior step. By integrating a pretrained flow model into the prior step via SI's reverse-time SDE and a novel timestep correction, FlowSGS reduces the number of network evaluations compared to plug‑and‑play diffusion samplers. Experiments demonstrate state‑of‑the‑art performance on various inverse problems, including the first flow‑based solution to a nonlinear inverse problem (Fourier phase retrieval).
By Tianao Li, Xinhui Qian, Emma Alexander
The paper introduces flow matching as an amortized alternative to Markov chain Monte Carlo for sampling from posterior distributions in Bayesian inverse problems. By training a transport map on joint samples of parameters and data, the method produces independent approximate posterior samples for any observation at negligible online cost, eliminating the need for new likelihood evaluations. The authors provide accuracy estimates in total‑variation distance and Kullback‑Leibler divergence, propose a hybrid Metropolized sampler for exactness, and validate the approach on examples such as electrical impedance tomography and a likelihood‑free Lotka‑Volterra model.
By Jan Blechschmidt, Oliver G. Ernst, Moritz Poguntke, Bj\"orn Sprungk
The paper introduces MS-Flow, a method that represents a flow-based generative model’s trajectory as a sequence of intermediate latent states instead of a single initial code. By enforcing local flow dynamics and coupling trajectory segments with matching penalties, the approach alternates between updating latent states and ensuring consistency with observed data. This strategy reduces memory usage and improves reconstruction quality on tasks such as image inpainting, super‑resolution, and computed tomography.
By Alexander Denker, Zeljko Kereta, Carola-Bibiane Sch\"onlieb, Moshe Eliasof
The paper introduces OCL-PDE, a generative framework for solving partial differential equation (PDE) inverse problems. It uses a learned observation‑complementary latent representation that retains reconstruction‑relevant information and combines it with observations to recover unknown fields. The method, built on a physics‑aware autoencoder and conditional Flow Matching, improves reconstruction accuracy and fine‑detail recovery compared to baseline approaches.
arXiv:2610. 09281v1 Announce Type: new Abstract: In Bayesian inverse problems, posterior sampling requires generating samples that are consistent with given observations while capturing the range of plausible solutions.
By Shiqin Zeng, Zijun Deng, Felix J. Herrmann
PosteriorBench is a new benchmark that evaluates how well generative inverse solvers recover full posterior distributions rather than just a single reconstruction. It tests four physics-based inverse problems—Darcy flow inversion, Poisson source recovery, carbon capture and storage, and light transport material inference—using high-fidelity reference posteriors generated by rejection sampling and MCMC. The benchmark employs five metrics (posterior-mean error, posterior-standard-deviation error, maximum mean discrepancy, sliced Wasserstein distance, and radially averaged power-spectrum error) to assess pointwise accuracy, uncertainty, distributional alignment, and global frequency fidelity, revealing significant distribution-matching gaps in current solvers and highlighting the importance of neural operators, guidance weights, and generation noise for posterior-variance calibration.
By Jiachen Yao, Zi-Siang Hsu, Xi Deng, Aditi Gupta, Xin Ju, Sally M Benson, Gege Wen, Anima Anandkumar
arXiv:2608. 05103v1 Announce Type: new Abstract: Data assimilation (DA) uses Bayesian inference to update the state of a numerical forecast model with observed data.
By Dibyajyoti Chakraborty, Romit Maulik
arXiv:2608. 05103v2 Announce Type: replace Abstract: Data assimilation (DA) uses Bayesian inference to update the state of a numerical forecast model with observed data.
By Dibyajyoti Chakraborty, Romit Maulik
FlowSGS introduces a flow-based posterior sampling method that combines Split Gibbs Sampling with annealed coupling and Stochastic Interpolants to improve flow priors for inverse imaging. The approach includes a novel timestep correction and accelerated warm-up using one-step flow models, resulting in faster and more accurate performance across various imaging tasks. It also demonstrates the first application of flow-based samplers to a nonlinear inverse problem, namely Fourier phase retrieval, and extends one-step flow models to principled Bayesian inverse imaging.
By Tianao Li, Xinhui Qian, Emma Alexander
The paper introduces the Ensemble-conditioned Inverse Problem (EIP), a multivariate statistical framework for inferring an ensemble that follows the pushforward of a prior through a forward process. It applies to fields such as high‑energy physics, full waveform inversion, and inverse imaging, and proposes non‑iterative inference‑time methods using ensemble inverse generative models that avoid explicit forward model use during inference. The authors demonstrate the approach on synthetic and real datasets and provide code for replication.
By Zhengyan Huan, Camila Pazos, Martin Klassen, Vincent Croft, Pierre-Hugues Beauchemin, Shuchin Aeron
TRACE is a retrospective streaming generative reconstruction framework designed to recover continuous physical fields from sparse, structured sensing streams. It performs approximate Bayesian inference in a continuous-coordinate latent space, fuses sparse off‑grid measurements with a state‑space temporal prior via Kalman‑style filtering, and refines past frames through retrospective smoothing. Experiments on active matter, ocean sound‑speed fields, and supernova simulations demonstrate that TRACE matches or surpasses existing frame‑wise generative reconstructors, offline spatiotemporal methods, and streaming data‑assimilation baselines in reconstruction quality under temporally sparse and spatially localized sensing protocols.
By Xinyu Zhang, Lihao Chen, Panqi Chen, Lei Cheng, Ting Zhang, Jianlong Li, Shikai Fang
arXiv:2507. 03094v2 Announce Type: replace-cross Abstract: Many challenges in scientific imaging involve solving ill-posed inverse problems, where the goal is to recover spatio-temporal fields from indirect, noisy, and highly sparse measurements - often without access to ground truth data or reliable simulators.
By Ali SaraerToosi, Renbo Tu, Esther Y. H. Lin, Kamyar Azizzadenesheli, Aviad Levis