This paper proposes a unified framework for inference-time augmentation to improve the robustness of physiological signal classification in real-world deployments.

The paper introduces a cross-attention Graph Neural Network (CrossAtt) that significantly improves the prediction of drug-drug interaction (DDI) mechanism types, demonstrating that explicit modeling o…

AutoForest is an end-to-end system that automatically generates publication-ready forest plots directly from biomedical papers, streamlining the labor-intensive process of meta-analysis.

The paper introduces REST-ASMR, a novel multimodal dataset combining PPG and behavioral responses to ASMR and nature videos, and demonstrates that a deep learning model can accurately predict ASMR tin…

This study explores using machine learning surrogates to accelerate complex numerical simulations of mechanical thrombectomy, achieving significant speedups but noting stability issues with complex ge…

Gyokuro is a novel Source-assisted Private Membership Testing (SPMT) protocol that uses Trusted Execution Environments (TEEs) to efficiently and privately verify data item existence in large databases…

The paper designed a minimalist BCMI system to translate EEG-measured emotional valence into adaptive music, but preliminary testing showed that frontal alpha asymmetry was not reliably modulated by i…

This paper analyzes the privacy challenges posed by Integrated Sensing and Communication (ISAC) in 6G networks by classifying sensitive data into three levels (location, behavioral, and physiological)…

The paper demonstrates that using synthetic hand images containing accessories, generated via inpainting, significantly improves the robustness of hand detectors for safety-critical applications by cl…

The paper introduces ArrythML, a highly efficient autoencoder-based TinyML model that enables accurate, low-power arrhythmia detection directly on resource-constrained embedded wearable devices.

The paper introduces CardioLens, a rigorous evaluation testbed for multi-sequence Cardiac MRI, which reveals that current Multimodal Large Language Models (MLLMs) exhibit a significant 'clinical reali…

The paper introduces PIGMENT, a physics-informed foundation model that enables reliable quantitative mapping of brain microstructure from extremely sparse or challenging diffusion MRI scans.

The paper proposes VDSB-GWSyn, a Diffusion Schrödinger Bridge framework, to synthesize controllable and anatomically feasible guidewire images on coronary angiography (CAG) scans, significantly improv…

The paper proposes using a mask-conditioned latent diffusion model to generate synthetic, labeled TEM images for data augmentation, achieving small but measurable performance improvements in defect de…

CodeCytos is a novel coding-based reasoning agent framework that enables dynamic, programmable interaction with spatial molecular imaging data, significantly improving the automation and customization…

The paper introduces Dual-Spectral Flow Matching (DSFM), a novel generative framework that uses wavelet and cosine transforms to synthesize highly realistic, non-stationary fMRI time series for improv…

The paper proposes Family-Grouped Hierarchical Federated Learning (Family-FL) combined with a highly optimized Tiny CNN-LSTM model to enable privacy-preserving ECG monitoring on ultra-resource-constra…

The paper proposes a multi-dimensional evaluation framework to assess EEG foundation models under realistic low-resource conditions, finding that while these models excel in long-context tasks, their…

The study demonstrates that LLMs exhibit significant, language-driven disparities in medical triage recommendations, recommending emergency care more frequently for English and Arabic prompts, even wh…

The paper proposes a novel convolutional block and optimization algorithm to implement resource-efficient 1D-CNNs for atrial fibrillation detection on tiny smart sensor systems, achieving high accurac…