arXiv Machine Learning June 2, 2026 By Magnus Bengtsson

Continuous Temporal Representations of Event-Based Signals via Interference-Based Wave Modeling

Read the original on arXiv Machine Learning →

arXiv:2605. 01270v2 Announce Type: replace Abstract: Spatio-temporal signals arising from event-driven biological processes, such as surface electromyography (sEMG), exhibit asynchronous and highly structured activation patterns that are challenging to model using conventional discrete or purely real-valued representations.

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

arXiv AI

Jun 19

SL-S4Wave: Self-Supervised Learning of Physiological Waveforms with Structured State Space Models

arXiv:2606. 19888v1 Announce Type: cross Abstract: Modeling long-sequence medical time series data, such as electrocardiograms (ECG), poses significant challenges due to high sampling rates, multichannel signal complexity, inherent noise, and limited labeled data.

By Feng Wu, Harsh Deep, Eric Lehman, Sanyam Kapoor, Guoshuai Zhao, Rahul Krishnan, Gari Clifford, Li-wei H Lehman

benchmarks

arXiv Machine Learning

Aug 6

Prototype-based Self-Supervised Multimodal Learning for PPG and Accelerometry Signals

arXiv:2510. 09764v2 Announce Type: replace Abstract: Modeling multi-modal time-series data is critical for capturing system-level dynamics, particularly in biosignals where modalities such as ECG, PPG, EDA, and accelerometry provide complementary perspectives on interconnected physiological processes.

By Wanting Mao, Maxwell A Xu, Harish Haresamudram, Mithun Saha, Santosh Kumar, James Matthew Rehg

rag multimodal

arXiv AI

Jun 30

Unified Complex-valued Neural Network: A Magnitude-Phase Computational Model for Event-Driven Neuromorphic Learning

arXiv:2606. 29099v1 Announce Type: cross Abstract: Artificial neural networks (ANN) provide accurate continuous-valued representation, whereas spiking neural networks (SNN) offer event-driven temporal processing, yet both paradigms face limitations when value encoding and timing dynamics must be learned within a single computational structure.

By Reza Ahmadvand, Sarah Safura Sharif, Yaser Mike Banad

arXiv Machine Learning

Jul 14

Event-based Neural Decoding for Neuroprosthetic Motor Control

arXiv:2607. 11445v1 Announce Type: new Abstract: A substantial number of patients experience diminished mobility due to disabilities, diseases, or accidents.

By Khaleelulla Khan Nazeer, Sirine Arfa, Matthias Jobst, Richard George, Christian Mayr

benchmarks

arXiv AI

Jun 12

Grammar of the Wave: Towards Explainable Multivariate Time Series Event Detection via Neuro-Symbolic VLM Agents

arXiv:2603. 11479v3 Announce Type: replace-cross Abstract: Time Series Event Detection (TSED) aims to localize semantically meaningful events in time series data, with critical applications in high-stakes domains.

By Sky Chenwei Wan, Yifei Y. Wang, Tianjun Hou, Xiqing Chang, Aymeric Jan

agents fine-tuning multimodal benchmarks

arXiv AI

Jun 2

LERD: Latent Event-Relational Dynamics for Neurodegenerative Classification

arXiv:2602. 18195v2 Announce Type: replace-cross Abstract: Alzheimer's disease (AD) alters brain electrophysiology and disrupts multichannel EEG dynamics, making accurate and clinically useful EEG-based diagnosis increasingly important for screening and disease monitoring.

By Yicheng Feng, Hairong Chen, Ziyu Jia, Samir Bhatt, Hengguan Huang

benchmarks

Related stories

SL-S4Wave: Self-Supervised Learning of Physiological Waveforms with Structured State Space Models

Prototype-based Self-Supervised Multimodal Learning for PPG and Accelerometry Signals

Unified Complex-valued Neural Network: A Magnitude-Phase Computational Model for Event-Driven Neuromorphic Learning

Event-based Neural Decoding for Neuroprosthetic Motor Control

Grammar of the Wave: Towards Explainable Multivariate Time Series Event Detection via Neuro-Symbolic VLM Agents

LERD: Latent Event-Relational Dynamics for Neurodegenerative Classification