data science

Exploring the experiences of medical sciences faculty members and students in using artificial intelligence applications: a qualitative descriptive study

The experiences of AI use among medical sciences faculty and students are context-dependent and conditional rather than uniformly positive or negative, highlighting the potential need for a pedagogical shift toward evaluative judgment and institutional support to bridge the geopolitical digital divide.

Fine-Tuning Generative Models for Extreme Events via CVaR-Penalized Wasserstein Gradient Flows

We propose CVaR-penalized Generative Particle Algorithm (CVaR-GPA), a robust, tail-agnostic algorithm for fine-tuning generative models to learn heavy-tailed distributions and capture extreme events, requiring no prior knowledge or estimation of the target's tail characteristics. The method is the Wasserstein gradient...

The impact of intratumor heterogeneity on outcome and resistance to therapy in primary breast cancer: a systematic review

Intratumor heterogeneity (ITH), the coexistence of diverse subclones within a single tumor, may pose a major challenge to effective chemotherapy in breast cancer. This cellular diversity contributes to treatment failure, residual disease, and early relapse by enabling tumor adaptation and therapeutic resistance. Althou...

Diagnostic accuracy of deep learning applied to liver MRI for hepatocellular carcinoma detection: a systematic review and HSROC meta-analysis of patient-level evidence

DL applied to liver MRI yielded promising model-derived patient-level summaries, but four retrospective, geographically concentrated cohorts do not establish a transportable accuracy benchmark, radiologist augmentation, or clinical benefit.

UltraGNN: A Sparse-Operator-Aware Framework for Accelerating Graph Neural Networks on Tensor Cores

Graph Neural Networks (GNNs) have achieved widespread success from social networks to AI-for-Science. Most existing GNN frameworks adopt scatter-first (edge-centric) or gather-first (vertex-centric) scheduling paradigms for message passing. However, these paradigms are closely tied to traditional CUDA-core execution mo...

Beyond Models: Building Trusted AI in the Age of Autonomous Agents

This presentation introduces the emerging paradigm of multi-agentic AI in cybersecurity, where systems evolve from passive tools to autonomous decision-making entities, and presents the concept of a "lethal trifecta of risks that redefine traditional security boundaries.

Diagnostic imaging modalities in Dyspnoea and suspected acute heart failure: a systematic review with Meta-analysis

Lung ultrasound may serve as a first-line bedside modality for detecting acute heart failure in adults with dyspnoea and CT showed high specificity based on limited evidence.

Implementing the NCATS translational science requirement: Approaches and challenges across multiple CTSA hubs

A Layered Simplex Architecture for Large Alphabets

Probability estimation over large alphabets under log loss is a well-studied problem, with celebrated methods such as the Good-Turing estimator. We introduce and study a new Bayesian estimator with four notable properties. First, its construction is exceptionally simple: multiply independent uniform draws from the prob...

The Recognition-Consequence Gap: How Gesture Recognition Misses Human Action

As computational systems that process multimodal behavioral streams (e.g., speech, gaze, facial expressions, gestures, and bodily movements) become increasingly capable, the field faces a critical question: does more embodied data necessarily yield deeper human understanding? This question is most visible in the gestur...

Aligning Gaze, Space, and Cognition: A Multimodal Triangulation Framework for Visitor Interactions in Cultural Heritage (An Expert vs. Non-Expert Comparative Study)

Cultural heritage, as a combination of physical space and cultural significance, relies heavily on a deep understanding of visitor interaction patterns for its active conservation and public education. However, existing research is largely confined to laboratory or virtual environments, failing to capture the embodied...

Artificial Intelligence, Gender, and the Technological Conversion Gap: A Research and Policy Agenda

The global expansion of artificial intelligence is reshaping organizations, labor markets, and innovation ecosystems at an unprecedented pace. Yet the governance of this transformation remains deeply gendered: women are systematically underrepresented in AI research, excluded from technology leadership pipelines, and m...