Product Alert

Jailbreaking Vision-Language Models Through the Visual Modality

The visual modality of vision-language models (VLMs) is an underexplored attack surface for bypassing safety alignment. We introduce four jailbreak attacks exploiting the vision component: (1) encoding harmful instructions as visual symbol sequences with a decoding legend, (2) replacing harmful objects with benign substitutes (e.g., bomb -> banana) then prompting for harmful actions using the subs...

From Prediction to Practice: A Task-Aware Evaluation Framework for Blood Glucose Forecasting

Clinical time-series forecasting is increasingly studied for decision support, yet standard aggregate metrics can obscure whether a model is actually useful for the task it is meant to serve. In safety-critical settings, low average error can coexist with dangerous failures in exactly the high-risk regimes that matter most. We present a task-aware evaluation framework for blood glucose forecasting...

Development and Validation of a Two-Stage NLP-LLM System for Automated Extraction of Deprescribing Recommendations from Discharge Summaries

Introduction: Polypharmacy in older adults is associated with increased risks of adverse drug events and functional decline. Discharge summaries often...

DrugPTM-Bench: A Large-Scale Dataset for Predictive Modeling of Drug-Induced Cell Type-Specific Protein Post-Translational Modifications

Protein post-translational modifications (PTMs), particularly phosphorylation, serve as the primary molecular switches that orchestrate cellular signa...

Artificial Intelligence for Cardiac Biomarkers After Myocardial Infarction: A Systematic Review and a Leakage-Aware Modeling Framework

Aims To systematically evaluate how artificial intelligence and machine-learning (AI/ML) methods are applied to cardiac biomarkers after myocardial in...

MTCurv: Deep learning for direct microtubule curvature mapping in noisy fluorescence microscopy images

Accurate quantification of the geometry of curvilinear biological structures is essential for understanding cellular mechanics and disease-related mor...

Edge AI for Automotive Vulnerable Road User Safety: Deployable Detection via Knowledge Distillation

Deploying accurate object detection for Vulnerable Road User (VRU) safety on edge hardware requires balancing model capacity against computational con...

Benchmarking OCR Pipelines with Adaptive Enhancement for Multi-Domain Retail Bill Digitization

The digitization of multi-domain retail billing documents remains a challenging task due to variability in scan quality, layout heterogeneity, and dom...

Dialysis Risk Prediction and Treatment Effect Estimation for AKI patients using Longitudinal Electronic Health Records

Progression to dialysis or end-stage renal disease is a rare but clinically important outcome. Clinicians need evidence on how medication exposures in...

Operational Feature Fingerprints of Graph Datasets via a White-Box Signal-Subspace Probe

Graph neural networks achieve strong node-classification accuracy, but their learned message passing entangles ego attributes, neighborhood smoothing,...

Semaglutide is associated with improved breast cancer survival, lower metastatic burden, and a dose-survival relationship uncoupled from weight-loss magnitude

Metabolic dysfunction is increasingly recognized as a risk factor for poor outcomes in breast cancer, but whether incretin-based therapies confer surv...

On the predictability of progression-free survival in ovarian cancer from NanoString gene expression data

In the treatment of high grade serous ovarian cancer (HGSC), patients initially diagnosed with unresectable tumors are first treated with neoadjuvant ...

Lightning Pose 3D: an uncertainty-aware framework for data-efficient multi-view animal pose estimation

Multi-view pose estimation is essential for quantifying animal behavior in scientific research, yet current methods struggle to achieve accurate track...

Learning Dynamic Representations and Policies from Multimodal Clinical Time-Series with Informative Missingness

Multimodal clinical records contain structured measurements and clinical notes recorded over time, offering rich temporal information about the evolut...

CHRep: Cross-modal Histology Representation and Post-hoc Calibration for Spatial Gene Expression Prediction

Spatial transcriptomics (ST) enables spatially resolved gene profiling but remains expensive and low-throughput, limiting large-cohort studies and rou...

Clinically Interpretable Sepsis Early Warning via LLM-Guided Simulation of Temporal Physiological Dynamics

Timely and interpretable early warning of sepsis remains a major clinical challenge due to the complex temporal dynamics of physiological deterioratio...

SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models

Reinforcement learning (RL) with verifiable rewards (RLVR) has demonstrated the great potential of enhancing the reasoning abilities in multimodal lar...

TwinTrack: Post-hoc Multi-Rater Calibration for Medical Image Segmentation

Pancreatic ductal adenocarcinoma (PDAC) segmentation on contrast-enhanced CT is inherently ambiguous: inter-rater disagreement among experts reflects ...

Aakhyan: An AI-Powered Vernacular Patient Communication Platform for Oncology in Resource-Limited Settings - System Architecture and Pilot Randomised Trial Protocol

Inadequate discharge communication is a well-documented contributor to medication non-adherence, missed follow-ups, and preventable readmissions acros...

Can LLMs Score Medical Diagnoses and Clinical Reasoning as well as Expert Panels?

Evaluating medical AI systems using expert clinician panels is costly and slow, motivating the use of large language models (LLMs) as alternative adju...