arXiv Machine Learning

RIPPLE: Generating Multi-Channel Phase, Not Recovering It

arXiv:2607. 27775v1 Announce Type: new Abstract: Generative models synthesize magnitude spectra with high fidelity, while phase is delegated to a recovery module---Griffin--Lim, a vocoder, or a latent decoder---applied independently to each channel.

arXiv Machine Learning

Jun 10

When Do Autoregressive Sequence Models Forecast Physical Wavefields? A Controlled Study on Synthetic Seismograms

arXiv:2606. 10868v1 Announce Type: new Abstract: Long-horizon autoregressive forecasting of oscillatory physical signals, such as seismograms, gravitational-wave strain, and similar wavefields is limited by error accumulation: as a causal model is fed its own outputs over hundreds of steps, small per-step errors compound into phase drift that pointwise metrics fail to detect.

By Waleed Esmail, Stuart Russell, Jana Klinge, Alexander Kappes, Christine Thomas

rag benchmarks

arXiv Machine Learning

Jul 27

IQ-JEPA: A Joint-Embedding Predictive Architecture with a Hermitian Vision Transformer for Sound Speed and Attenuation Estimation from Ultrasound IQ Data

arXiv:2607. 22351v1 Announce Type: new Abstract: The speed of sound in tissue is a prerequisite for well-focused imaging and has diagnostic value, but recovering it from raw pulse-echo channel data is fundamentally a nonlinear inverse problem.

By Masashi Sode, Gianmarco Pinton

llms rag computer-vision fine-tuning

arXiv Machine Learning

Jun 3

Data-Driven Forecasting of three-Component Seismograms Using Transformer Architectures

arXiv:2606. 02912v1 Announce Type: cross Abstract: Forecasting seismic waveforms beyond observed data remains challenging due to the nonlinear, dispersive, and multi-scale nature of seismic wave propagation.

By Waleed Esmail, Stuart Russell, Jana Klinge, Alexander Kappes, Christine Thomas

llms

arXiv Machine Learning

Aug 7

Perfect reconstruction of sparse signals using nonconvexity control and one-step RSB message passing

arXiv:2512. 17426v2 Announce Type: replace-cross Abstract: We consider sparse signal reconstruction via minimization of the smoothly clipped absolute deviation (SCAD) penalty, and develop one-step replica-symmetry-breaking (1RSB) extensions of approximate message passing (AMP), termed 1RSB-AMP.

By Xiaosi Gu, Ayaka Sakata, Tomoyuki Obuchi

arXiv Machine Learning

Jun 11

Spectrally Regularized Latent Flow Matching for Turbulence Generation

arXiv:2606. 11691v1 Announce Type: new Abstract: Latent diffusion and flow matching have emerged as leading approaches for synthetic turbulence generation, yet they systematically under-represent dissipation-range amplitudes.

By Khalid Rafiq, Aditya G. Nair

diffusion safety

arXiv Machine Learning

Jun 30

Two kinds of robustness are not the same: disentangling fault tolerance and low-SNR robustness in multi-domain event detection on real data

arXiv:2606. 29339v1 Announce Type: cross Abstract: Reliable event detection underpins induced-seismicity monitoring for Carbon dioxide Capture and Storage (CCS) and geothermal operations, distributed acoustic sensing (DAS), and industrial condition monitoring.

By Isao Kurosawa

llms benchmarks

arXiv Machine Learning

Jun 8

On the conditional equivalence of phase retrieval algorithms

arXiv:2606. 07257v1 Announce Type: cross Abstract: Phase retrieval - recovering a complex-valued field from intensity measurements - is typically solved using variants of the Gerchberg-Saxton (GS) algorithm, understood as alternating projections between measurement planes.

By Jakob Schroeder, Andreas D\"opp

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 Machine Learning

Jun 10

When to Align, When to Predict: A Phase Diagram for Multimodal Learning

arXiv:2606. 11190v1 Announce Type: new Abstract: Cross-modal alignment (CA) and cross-modal prediction (CP) are the dominant paradigms for multimodal representation learning, yet there is no systematic understanding of when each succeeds, when each fails, and when cross-modal training helps at all -- a gap that leaves practitioners, especially in scientific domains like biomedicine or astrophysics, with heterogeneous instruments and multiple levels of organization and measurement, unable to diagnose why standard methods underperform the best single modality.

By Ilay Kamai, Hugues Van Assel, Aviv Regev, Hagai B. Perets, Randall Balestriero

multimodal benchmarks safety

arXiv Machine Learning

Jun 2

Torus Graphs for Large Scale Neural Phase Analysis

arXiv:2606. 00496v1 Announce Type: new Abstract: Oscillatory neural signals such as electroencephalography (EEG) and local field potentials (LFPs) show phase relationships that coordinate communication across brain regions.

By Jack Goffinet, Casey Hanks, David E. Carlson

arXiv Machine Learning

Jul 28

Restoration Flow Matching-Based Channel Refinement and Equalization Correction for MIMO Semantic Communications

arXiv:2607. 23615v1 Announce Type: new Abstract: In multiple-input multiple-output (MIMO) semantic communication, imperfect channel state information (CSI) and equalization mismatch can seriously degrade semantic reconstruction quality.

By Wenkai Liu, Nan Ma, Jianqiao Chen, Xiaodong Xu, Meixia Tao, Ping Zhang

diffusion

arXiv AI

Jun 4

An Empirical Audit of Input Encoders for Multi-Channel Signal Transformers

arXiv:2606. 04752v1 Announce Type: cross Abstract: Transformers consuming multi-channel scalar signals must embed $C$ simultaneous values into one $d_{\text{model}}$-dimensional vector per time step.

By Ossi Lehtinen

llms benchmarks

Related stories