arXiv Machine Learning June 16, 2026 By Hojin Kim, Dibyajyoti Chakraborty, Takahiko Toki, Carlo Scalo, Romit Maulik

Multiscale Hypersonic Boundary Layer Reconstruction via Spectral Binning and Subdomain-wise Conditional Diffusion

Read the original on arXiv Machine Learning →

arXiv:2606. 15023v1 Announce Type: cross Abstract: We propose a multiscale probabilistic reconstruction framework for hypersonic Couette flow, where near-wall states are inferred from limited top-wall observations using conditional diffusion model.

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

diffusion

arXiv Machine Learning

Jun 24

NeuroSonic: Conditional Flow Matching for EEG-to-Speech Reconstruction

arXiv:2606. 24087v1 Announce Type: new Abstract: Reconstructing continuous speech from scalp electroencephalography (EEG) remains fundamentally challenging.

By Wenhao Gao, Yifan Wang, Yijia Ma, Carl Yang, Wen Li, Chenyu You

llms diffusion benchmarks

arXiv AI

Aug 3

Patch-Based 3D Variational Autoencoder for Super-Resolution of Turbulent Channel Flow

arXiv:2507. 22082v2 Announce Type: replace-cross Abstract: Direct numerical simulation (DNS) accurately resolves all spatio-temporal scales of wall-bounded turbulence but becomes prohibitively expensive as the Reynolds number increases.

By Anuraj Maurya

diffusion

arXiv AI

Aug 10

From Points to Edges: Edge-Conditioned Spectral Operators for Physics-Sensitive PDE Learning

arXiv:2608. 06894v1 Announce Type: new Abstract: Neural operators have become a central tool for solving partial differential equations (PDEs), with spectral operators offering efficient global mixing across spatial locations.

By Zhentao Tan, Ruijie Quan, Yi Yang

benchmarks

arXiv Machine Learning

Jun 30

Guided Unconditional and Conditional Generative Models for Super-Resolution and Inference of Quasi-Geostrophic Turbulence

arXiv:2507. 00719v3 Announce Type: replace-cross Abstract: Typically, numerical simulations of Earth systems are coarse, and Earth observations are sparse and gappy.

By Anantha Narayanan Suresh Babu, Akhil Sadam, Pierre F. J. Lermusiaux

diffusion

arXiv Machine Learning

Jun 5

Wall Shear Stress Reconstruction from Concentration: Differentiable Physics and Physics-Informed Neural Networks

arXiv:2606. 06313v1 Announce Type: cross Abstract: Wall shear stress (WSS) governs near-wall transport dynamics and is a key hemodynamic indicator in cardiovascular flows, yet remains difficult to infer accurately due to the need for precise computation of near-wall velocity gradients.

By Mahmoud Elhadidy, Siva Viknesh, Roshan M. D'Souza, Amirhossein Arzani

benchmarks

arXiv AI

Jun 15

A fully GPU-based workflow for building physics emulators of hypersonic flows

arXiv:2606. 13742v1 Announce Type: cross Abstract: The ability to resolve complex physical phenomena with high fidelity and at low computational cost is central to addressing key challenges in modern engineering.

By Fabian Paischer, Dylan Rubini, Deniz A. Bezgin, Aaron B. Buhendwa, David Hauser, Florian Sestak, Johannes Brandstetter, Sebastian Kaltenbach, Nikolaus A. Adams

Related stories

NeuroSonic: Conditional Flow Matching for EEG-to-Speech Reconstruction

Patch-Based 3D Variational Autoencoder for Super-Resolution of Turbulent Channel Flow

From Points to Edges: Edge-Conditioned Spectral Operators for Physics-Sensitive PDE Learning

Guided Unconditional and Conditional Generative Models for Super-Resolution and Inference of Quasi-Geostrophic Turbulence

Wall Shear Stress Reconstruction from Concentration: Differentiable Physics and Physics-Informed Neural Networks

A fully GPU-based workflow for building physics emulators of hypersonic flows