The paper presents a machine‑learning framework for reconstructing absorption and scattering coefficients in bilayered biological media from single‑distance, time‑resolved reflectance data. By training on a synthetic dataset generated with exact Monte Carlo simulations, the method outperforms traditional diffusion‑equation‑based inverse solvers in both speed and accuracy. It also estimates the dimensionality of the parameter space without prior knowledge of the number of layers, and suggests that future work could further improve accuracy using multi‑distance data.
By Caterina Amendola, Giulia Maffeis, Lorenzo Buffoni, Lorenzo Chicchi, Francesco Coghi, Duccio Fanelli, Raffaele Marino, Fabrizio Martelli, Riccardo Paoli, Lorenzo Pattelli, Lorenzo Spinelli
Score-based diffusion models, a recent framework for posterior sampling in Bayesian inverse problems, are applied to diffuse optical tomography (DOT), a highly ill‑posed boundary value problem for recovering tissue absorption and scattering. The authors introduce a mixed score that combines a learned component with a model‑based component, providing a theoretical justification for its local approximation to the true score in the small diffusion‑time regime. Four difference‑imaging approaches are compared—classical model‑based, approximate diffusion, exact posterior sampling (UCoS), and a regularized UCoS—showing that UCoS yields more accurate reconstructions, especially under limited‑view geometry and real experimental data.
By Fabian Schneider, Meghdoot Mozumder, Konstantin Tamarov, Leila Taghizadeh, Tanja Tarvainen, Tapio Helin, Duc-Lam Duong
The paper presents a method for training single‑step neural surrogates that can handle wave‑scattering problems with tens of thousands of controllable variables. By dynamically generating training examples that highlight surrogate errors and using a replay dataset with normalization, the authors achieve a surrogate that accurately simulates two‑dimensional wave scattering for up to 41,772 variables and generalizes to over 3 million variables without retraining. The surrogate is applied to forward simulations and inverse design of freeform beam splitters and gradient‑index lenses, achieving speedups up to 26.5× compared to traditional FDTD methods.
By Charles Dove, Laura Waller
The paper presents a method for training single‑step neural surrogates that can handle wave‑scattering inverse problems with tens of thousands of controllable variables. By dynamically generating training examples through gradient ascent and using a replay dataset with normalization, the authors achieve a surrogate that accurately models two‑dimensional wave scattering for up to 41,772 variables and can generalize to over 3 million variables without retraining. The surrogate demonstrates comparable or better performance than traditional FDTD simulations for large‑scale forward simulations and inverse design of photonic devices, achieving speedups up to 26.5×.
arXiv:2608. 09382v1 Announce Type: cross Abstract: Electromagnetic inverse scattering is a nonlinear and ill-posed problem, where accurate reconstruction is challenging due to measurement limitations, noise, and high computational costs, especially for 3-D imaging.
By Yutong Du, Zicheng Liu, Bo Qi, Yali Zong, Peixian Han
Generative Monte Carlo (GMC) is a new particle transport simulation method that embeds generative AI into solving the linear Boltzmann equation. By treating cell transmission as a conditional generation task, neural networks trained with conditional flow matching produce particle exit states—position, direction, and path length—without simulating scattering histories. GMC generalizes across materials using optical coordinate scaling, matches standard Monte Carlo’s statistical accuracy and convergence, and achieves constant‑cost per cell transmission, offering significant speedups in optically thick regimes.
By Joseph A. Farmer, Aidan Murray, Johannes Krotz, Ryan G. McClarren
The paper introduces a coordinate-residual physics-driven neural network (CRPDNN) for 3‑D electromagnetic inverse scattering. CRPDNN models the unknown contrast distribution using normalized spatial coordinates and a residual convolutional network, optimizing parameters by enforcing consistency between measured and predicted scattered fields. It eliminates the need for preliminary reconstruction, achieving lower relative error and significant speedups compared to existing methods, while maintaining stability under noisy measurements and showing promise in practical imaging experiments.
By Yutong Du, Zicheng Liu, Bo Qi, Yali Zong, Peixian Han
arXiv:2606. 03262v1 Announce Type: new Abstract: Neural operators learn mappings between infinite-dimensional function spaces and provide a data-driven surrogate modeling paradigm for parametric partial differential equations (PDEs).
By Keke Wu, Yixuan Zhang, Jingrun Chen
arXiv:2605.29016v2 Announce Type: replace-cross
Abstract: We investigate conditional diffusion modeling for three-dimensional 21 cm lightcone emulation, focusing on cubes with a sky-plane size of $64...
By Bin Xia, John H. Wise
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:2607. 23469v1 Announce Type: cross Abstract: Photonic-crystal surface-emitting lasers (PCSELs) can combine high-power operation with narrow-divergence surface emission, but optimizing coupled parameters requires costly full-wave simulations.
By Longying Wen, Feiyang Wu, Jinglin Yu, Chongxian Yuan, Renjie Li, Zhaoyu Zhang
VolS-GS is a relightable Gaussian splatting framework that reconstructs objects from one-light-at-a-time captures and renders them under novel lighting and viewpoints. It addresses the difficulty of modeling non‑local effects such as subsurface scattering by using the spatial support of the Gaussian scene as the domain of a differentiable finite‑volume transport solver, allowing light to propagate through the object's interior. A small network predicts scattering and absorption coefficients for each Gaussian, and the solver redistributes incident light, while a shadow term and regularizer prevent learned shadow and specular terms from dominating the appearance.
"whyItMatters":"The approach improves relighting quality on held‑out lights and views across three OLAT benchmarks, demonstrating its effectiveness for realistic rendering of subsurface scattering effects."
By Junyeong Ahn, Jaegul Choo