Devices and Vaccines

EdgeDiT: Hardware-Aware Diffusion Transformers for Efficient On-Device Image Generation

Diffusion Transformers (DiT) have established a new state-of-the-art in high-fidelity image synthesis; however, their massive computational complexity and memory requirements hinder local deployment on resource-constrained edge devices. In this paper, we introduce EdgeDiT, a family of hardware-efficient generative transformers specifically engineered for mobile Neural Processing Units (NPUs), such...

DreamLite: A Lightweight On-Device Unified Model for Image Generation and Editing

Diffusion models have made significant progress in both text-to-image (T2I) generation and text-guided image editing. However, these models are typically built with billions of parameters, leading to high latency and increased deployment challenges. While on-device diffusion models improve efficiency, they largely focus on T2I generation and lack support for image editing. In this paper, we propos...

An Energy-Efficient Spiking Neural Network Architecture for Predictive Insulin Delivery

Diabetes mellitus affects over 537 million adults worldwide. Insulin-dependent patients require continuous glucose monitoring and precise dose calcula...

ROAST: Risk-aware Outlier-exposure for Adversarial Selective Training of Anomaly Detectors Against Evasion Attacks

Safety-critical domains like healthcare rely on deep neural networks (DNNs) for prediction, yet DNNs remain vulnerable to evasion attacks. Anomaly det...

Predicting Infant Nonattendance at the Next Recommended Well-Child Visit: Model Development and Validation

BackgroundWell-child visits (WCVs) are essential for preventive care, yet missed appointments often lead to delayed interventions. We developed and va...

Associative Memory using Attribute-Specific Neuron Groups-2: Learning and Sequential Associative Recall between Cue Neurons for different Cue Balls

This paper introduces a neural network model that learns multiple attributes as images and performs associated, sequential recall of the learned memor...

CIAR: Interval-based Collaborative Decoding for Image Generation Acceleration

Auto-regressive (AR) models have recently made notable progress in image generation, achieving performance comparable to diffusion-based approaches. H...

Large-Scale Avalanche Mapping from SAR Images with Deep Learning-based Change Detection

Accurate change detection from satellite imagery is essential for monitoring rapid mass-movement hazards such as snow avalanches, which increasingly t...

HiFiGaze: Improving Eye Tracking Accuracy Using Screen Content Knowledge

We present a new and accurate approach for gaze estimation on consumer computing devices. We take advantage of continued strides in the quality of use...

RNASTOP: A Deep Learning Framework for mRNA Chemical Stability Prediction and Optimization

Messenger RNA (mRNA) vaccines offer promising therapeutics for combating various diseases, yet their inherent chemical instability hampers their long-...

STEP: Detecting Audio Backdoor Attacks via Stability-based Trigger Exposure Profiling

With the widespread deployment of deep-learning-based speech models in security-critical applications, backdoor attacks have emerged as a serious thre...

Context-Aware Emergency Department Triage Using Pairwise Comparisons and Bradley-Terry Aggregation

Objective: To evaluate a ranking approach for emergency department (ED) waiting room prioritization that uses pairwise clinical comparisons aggregated...

KidsNanny: A Two-Stage Multimodal Content Moderation Pipeline Integrating Visual Classification, Object Detection, OCR, and Contextual Reasoning for Child Safety

We present KidsNanny, a two-stage multimodal content moderation architecture for child safety. Stage 1 combines a vision transformer (ViT) with an obj...

Antenatal surveillance of placental function using a wearable near infrared spectroscopy device with machine learning data interpretation

Background Placental dysfunction remains a leading cause of stillbirth and neonatal morbidity, yet current monitoring tools provide only indirect and ...

Prompting with the human-touch: evaluating model-sensitivity of foundation models for musculoskeletal CT segmentation

Promptable Foundation Models (FMs), initially introduced for natural image segmentation, have also revolutionized medical image segmentation. The incr...

Evaluating Few-Shot Pill Recognition Under Visual Domain Shift

Adverse drug events are a significant source of preventable harm, which has led to the development of automated pill recognition systems to enhance me...

A Universal, AI-based Design Framework for Efficient Manufacturing of mRNA Therapeutics

The growth of mRNA therapeutics is limited by bespoke manufacturing processes. To overcome this barrier to access and innovation, we introduce an AI-d...

TrainDeeploy: Hardware-Accelerated Parameter-Efficient Fine-Tuning of Small Transformer Models at the Extreme Edge

On-device tuning of deep neural networks enables long-term adaptation at the edge while preserving data privacy. However, the high computational and m...

Extracting patient reported cannabis use and reasons for use from electronic health records: a benchmarking study of large language models

Objective To develop and evaluate a scalable and reproducible natural language processing (NLP) approach using large language models (LLM), to identif...

Synthetic Defect Image Generation for Power Line Insulator Inspection Using Multimodal Large Language Models

Utility companies increasingly rely on drone imagery for post-event and routine inspection, but training accurate defect-type classifiers remains diff...