Risk Management

Certifying What Helps Customer-Return Timing: A Screen-and-Confirm Test for Conditioning Signals, and Why Decay Is Nearly Enough

Practitioners enrich customer-return models with ever more signals (lifetime value, category, recency/frequency, calendar, geography), and the temporal-point-process (TPP) literature follows suit with covariate- and external-covariate-conditioned intensities. But does any of it improve the timing, and how would you know? A null ("feature X doesn't help") is only meaningful if the model could have ...

When Offline Evaluation Misleads: A Diagnostic Protocol for Reward and Policy Selection in Delayed-Feedback Contextual Bandits

Personalizing marketing messages with contextual multi-armed bandits (CMABs) drives real business value, yet the objective that ultimately matters - a downstream conversion - is observed only weeks later, too late to drive online learning. Teams therefore train the bandit on a fast proxy reward, and separately must judge whether a contextual bandit is worth its complexity over sending one best mes...

A comparison of CNN architectures for Alzheimer's disease detection in single-view MRI scans

Alzheimer's disease is a leading cause of death with no cure. Therefore, early detection is critical to slow progression and preserve quality of life....

Do Not Forget the Obvious - RISC: A Risk-Informed Slice-Coverage Protocol for Safe Autonomous Driving

Aggregate metrics may not fully reflect performance in insufficiently examined high-risk driving conditions. We propose RISC (Risk-Informed Slice Cove...

Few-Shot Ordinal Learning for Day-Wise Freshness Estimation with Hyperspectral Fish Images

Non-destructive food quality assessment has increasingly benefited from hyperspectral imaging (HSI), which captures spectral signatures linked to bioc...

SafeCap: Improving LVLM Safety with Image Captioning Reinforcement Learning

Large vision-language models (LVLMs) remain vulnerable to jailbreak attacks that exploit visual inputs to bypass safety alignment inherited from their...

Retrieval-Augmented Vision Foundation Models for Robust Leukemia Cell Classification across Multiple Microscopy Datasets

Leukemia cell image classification is challenged by real-world domain shifts from acquisition, staining, illumination, and site protocols, causing sin...

SCOUT: Symmetric Consensus Outlier Detection for Failure Localization in LLM Pre-Training

In LLM pre-training, synchronization propagates rank-local stalls, slowdowns, and numerical errors into job-wide symptoms, obscuring their origin. Exi...

CapProbe: Evaluating Detailed Image Captions via Full-Scene Dense Question Answering

Evaluating detailed image captions from Vision-Language Models (VLMs) requires going beyond surface-level semantic similarity. Reference-based metrics...

Sci-VBench: Evaluating Knowledge- and Reasoning-Intensive Video Generation in Science Domains

We introduce Sci-VBench, a comprehensive benchmark for evaluating knowledge- and reasoning-intensive video generation across scientific domains. It co...

ToolVision: Learning When and How to Use Visual Tools with Capability-Aligned Supervision

Thinking with images allows a multimodal model to compensate for limited perception by invoking visual tools through code. Yet the prevailing SFT-then...

Characterizing large language model generative artificial intelligence variability in the production of objective structured clinical examination stations

Background. Designing high-quality Objective Structured Clinical Examination (OSCE) stations is a time-consuming process. Generative artificial intell...

Privacy-Preserving Action Recognition: Taxonomy, Methods, and Privacy-Utility Trade-offs

Video surveillance in public safety, healthcare, and smart environments has made continuous human monitoring routine, raising real risks to personal i...

Canonical Joint Energy-Based Model on CIFAR-10: failure modes and practical indistinguishability of Predictor-Corrector and SGLD samplers

Joint Energy-Based Models (JEM) unify classification and generation within a single network and support out-of-distribution (OOD) detection. Canonical...

Quantization Effects on Biomedical LLM Reliability

When decoder language models are used as classifiers, predicted class probabilities depend on implementation choices, including the prompt template, v...

NeuroAid An Open-Data Multimodal Screening Framework for Parkinson's and Depression Risk Estimation

Neurological and mental-health conditions such as Parkinson's disease (PD) and major depressive disorder (MDD) impose a substantial and growing global...

Predictive models for hospitalization and mortality in dengue using SINAN data: study protocol for development, temporal validation, and performance evaluation

Background: Dengue continues to place a heavy clinical and organizational burden on health care systems, particularly during epidemics, when the high ...

Non-Invasive Embryo Quality Assessment via Matrix-Optimized Untargeted LC-MS Metabolomics of Spent Embryo Culture Media and Weighted Ensemble Machine Learning

Spent embryo culture media (SECM) presents significant challenges for untargeted LC-MS metabolomics due to limited sample volume, high salt content, a...

Trust-Aware Topology Learning for Dynamic Decentralized Federated Learning under Adversaries

In dynamic mobile decentralized federated learning (DFL), adversaries can poison both model updates and the topology information devices use to choose...

Surrogate Substitution Preserves PHI Detectability: A Multi-Detector Equivalence Study

Structure-preserving de-identification replaces protected health information (PHI) with realistic same-type surrogates -- "Anna S." becomes "Maria S."...