Cultural Competence

An Interpretable Cost-Aware Framework for Mitigating Bias in Skin Lesion Classification Across Diverse Skin Tones

Despite advances in dermatological AI, skin lesion predictions continue to exhibit significant bias, consistently exhibiting underperformance in brown and darker tones. This disparity stems largely from the lack of representation in commonly used datasets such as Fitzpatrick17k and Diverse Dermatology Images (DDI), which are heavily skewed toward lighter skin tones. Existing models, including thos...

LeakageBench: Document-Level Leakage Risk for Redacting Personally Identifiable Information in Document Images

Real-world personally identifiable information (PII) redaction often operates on document images---scans, screenshots, and PDF renderings---where OCR errors, layout structure, and visual noise determine whether sensitive information is actually removed. Existing PII benchmarks are mostly text-centric and do not measure document-level redaction risk: a page remains unsafe if even one identifier is ...

GNMCADS: Sampling For Protein Conformation Diversity With Gaussian Network Model Guided Condition Annealed Diffusion Sampler

Proteins are dynamic molecules existing in diverse conformational states underlying their biological functions. Although recent approaches have enable...

FairLens: Benchmarking Fairness in Vision-Language Models for High-Stakes Decision-Making

Vision-language models (VLMs) are increasingly used to make decisions from visual inputs. We introduce FAIRLENS, a benchmark and evaluation framework ...

Beneath the Diff: Diagnosing and Mitigating Algorithmic Mode Collapse in Code-Level Autonomous Research Loops

Code-level autonomous research loops (ARLs) have recently emerged as a concrete object of study in automated machine learning research. In such loops,...

CHARMS and PROBAST+AI: an updated template for Data Extraction and Risk of Bias Assessment in systematic reviews of prediction models

Background: Systematic reviews of clinical prediction models increasingly include studies using artificial intelligence (AI) and machine learning (ML)...

Centering before Pruning: Lightweight Geometry Correction for Diversity-Based Visual Token Pruning in LVLMs

Large vision-language models (LVLMs) incur substantial inference costs due to their long and highly redundant visual-token sequences. Diversity-based ...

Learning Dynamics of Logits Debiasing for Long-Tailed Semi-Supervised Learning

Long-tailed distributions are prevalent in real-world semi-supervised learning (SSL), where pseudo-labels tend to favor majority classes, leading to d...

Guardrail-Agnostic Societal Bias Evaluation in Large Vision-Language Models

We propose a societal bias evaluation method for large vision-language models (LVLMs) in the era of strong safety guardrails. Existing benchmarks rely...

ContextBias: Controlled Evaluation of Bias Persistence Under Context Shift in Text-to-Image Models

Text-to-image models learn associations between concepts - in the case of this paper, people's professions, which we refer to as roles - and visual at...

Volatile profiling and estimated odor-activity analysis of commercial drug-type cannabis accessions

Volatile organic compounds (VOCs) define the distinctive aroma of cannabis and critically influence consumer preference, cultivar authentication, and ...

Cross cohort oral microbiome meta-analysis identifies shared OPMD OSCC dysbiosis while machine learning exposes limits of OSCC classifier transportability

Oral potentially malignant disorders (OPMDs) precede a subset of oral squamous cell carcinomas (OSCCs), but microbiome studies are difficult to compar...

FVeinSyn: Synthetic Finger Vein Image Generator

A major challenge in finger vein recognition is the lack of large-scale public datasets. Existing datasets contain few identities and limited samples ...

GGSS: Geodesic-Gated Spherical Steering for Inference-Time Debiasing of Generative Vision-Language Models

Generative vision-language models (VLMs) are increasingly used in human-centered settings, yet they can produce demographically biased outputs even wh...

Controlling for Omitted Variable Bias in Deep Neural Networks

Control variables are widely used in statistical modelling to account for omitted variable bias of known confounders. However, they have largely been ...

Geographical targeting of active case finding for tuberculosis in Pakistan using artificial intelligence software: a qualitative study embedded within the SPOT TB trial

Background: Tuberculosis (TB) remains a critical public health challenge in Pakistan. The SPOT-TB trial evaluated MATCH-AI; an AI tool designed to geo...

Clustering and Token Denoising for Faster and More Robust VLMs

Recent Visual-Language Models (VLMs) have enhanced the capabilities of pre-trained LLMs by adding vision tokens alongside text, with approaches like L...

Learning-State-Aware Dynamic Generative Data Augmentation on Small-Scale Datasets

Small-scale image classification is often limited by the scarcity of training data. Generative data augmentation (GDA) based on pretrained generative ...

Performance of an Ambient Generative AI Documentation Tool in a Linguistically Diverse Clinical Setting

Ambient artificial intelligence scribes are being increasingly used in healthcare to improve efficiency and reduce provider clinical documentation bur...

Discovery and Spatial Characterisation of Multiple Shortcut Groups for Auditing Vision Model Bias

Deep learning models trained on datasets with spurious correlations can achieve high average accuracy whilst relying on shortcut features that do not ...