Clinical Trials

Efficient Streaming Algorithms for Two-Dimensional Congruence Testing and Geometric Hashing

The geometric congruence problem is a fundamental building block in many computer vision and image recognition tasks. This problem considers the decision task of whether two point sets are congruent under translation and rotation. A related and more general problem, geometric hashing, considers the task of compactly encoding multiple point sets for efficient congruence queries. Despite its wide ap...

TRACE: Temporal Reasoning via Agentic Context Evolution for Streaming Electronic Health Records (EHRs)

Large Language Models (LLMs) encode extensive medical knowledge but struggle to apply it reliably to longitudinal patient trajectories, where evolving clinical states, irregular timing, and heterogeneous events degrade performance over time. Existing adaptation strategies rely on fine-tuning or retrieval-based augmentation, which introduce computational overhead, privacy constraints, or instabilit...

The scaffolding of individual variability in language processing by domain-general neural networks

Language processing is supported by distributed neural systems. Yet most research examines these systems at the population-average level, obscuring ho...

Free Lunch in Medical Image Foundation Model Pre-training via Randomized Synthesis and Disentanglement

Medical image foundation models (MIFMs) have demonstrated remarkable potential for a wide range of clinical tasks, yet their development is constraine...

DeepSight: An All-in-One LM Safety Toolkit

As the development of Large Models (LMs) progresses rapidly, their safety is also a priority. In current Large Language Models (LLMs) and Multimodal L...

Neural Dynamics of Automatic Speech Production

Speech is a defining human behavior, and this ability depends critically on speech motor cortex. While the ventral precentral and postcentral gyri are...

Development and retrospective validation of SCOUT: scalable clinical oversight of large language models via uncertainty triangulation

Large language models (LLMs) are increasingly used in clinical workflows, yet requiring clinician review of every AI output negates the efficiency gai...

Benchmarking Large Language Models for Intensive Care Unit Clinical Decision Support: A Dual Safety Evaluation of 26 Models on Consumer Hardware

Background: Large Language Models (LLMs) show promise for clinical decision support in Intensive Care Units (ICU), but their safety and reliability re...

When the Prompt Becomes Visual: Vision-Centric Jailbreak Attacks for Large Image Editing Models

Recent advances in large image editing models have shifted the paradigm from text-driven instructions to vision-prompt editing, where user intent is i...

Perception with Guarantees: Certified Pose Estimation via Reachability Analysis

Agents in cyber-physical systems are increasingly entrusted with safety-critical tasks. Ensuring safety of these agents often requires localizing the ...

Early Detection of Absurdity Signals in Pharmacovigilance: A Machine Learning Ensemble Approach to Identify Rare Adverse Drug Reactions

Background: Traditional pharmacovigilance methods based on biostatistical approaches systematically exclude outliers and rare events, potentially miss...

A Causal Machine Learning Framework for Treatment Personalization in Clinical Trials: Application to Ulcerative Colitis

Randomized controlled trials estimate average treatment effects, but treatment response heterogeneity motivates personalized approaches. A critical qu...

Robustness of Vision Language Models Against Split-Image Harmful Input Attacks

Vision-Language Models (VLMs) are now a core part of modern AI. Recent work proposed several visual jailbreak attacks using single/ holistic images. H...

MPIB: A Benchmark for Medical Prompt Injection Attacks and Clinical Safety in LLMs

Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) systems are increasingly integrated into clinical workflows; however, prompt inj...

The hidden risks of temporal resampling in clinical reinforcement learning

Offline reinforcement learning (ORL) has shown potential for improving decision-making in healthcare. However, contemporary research typically aggrega...

Safety and Utility of an Agentic Large Language Model-Based Hospital Course Summarizer: A Prospective Real-World Pilot Study

Importance: High-quality discharge summaries are essential for safe care transitions but contribute substantially to clinician documentation burden an...

GRP-Obliteration: Unaligning LLMs With a Single Unlabeled Prompt

Safety alignment is only as robust as its weakest failure mode. Despite extensive work on safety post-training, it has been shown that models can be r...

Drug Safety Agents Using Graphs and Ontologies

In pharmacovigilance, analyzing drug safety cases is often time consuming due to the abundance of laboratory data, complex medical histories, and intr...

Multimodal Imaging-Based Targeting Approach for Network-Level Brain Stimulation

Background: Neural network effects of transcranial direct current stimulation (tDCS) are poorly understood. Here, we introduce an empirically informed...

Do Large Language Models Read or Remember? Analyzing LLM Performance in Biomedical Text Mining With Progressive Content Removal and Counterfactual Results

Purpose: Large language models (LLMs) can classify biomedical documents accurately, but strong performance does not prove they are using the supplied ...