Category: Publications

Large language models as judges: recent advances in LLM-based evaluation, critique, preference modeling, and feedback for text and code (2026)

Artificial Intelligence Review Authors M. Nadăş Abstract Large Language Models (LLMs) are increasingly used as judges to evaluate, rank, and critique AI-generated text and code. This survey provides a comprehensive overview of recent advances (2020–early 2026) in LLM-based evaluation, covering techniques, applications, and challenges across domains. We make three main contributions: (1) a unified…

Transformer-Based Anomaly Detection for Neurodegenerative Screening in MRI Images. (2026)

International Journal of Neural Systems Authors Enol García González, Mădălina Dicu, José R. Villar, Camelia Chira Abstract The automatic detection of anomalies in medical images is a significant challenge in the assisted diagnosis of neurodegenerative diseases such as Alzheimer’s. This paper presents an anomaly detection model based on Transformers for the analysis of brain…

A Systematic Analysis of Data Augmentation and Training Parameters for Lightweight CNN-Based Mammographic Lesion Classification (2026)

Hybrid Artificial Intelligence Systems Authors D. Trandafir, Mădălina Dicu, Camelia Chira Abstract Breast cancer remains a major cause of cancer-related mortality among women worldwide, making accurate lesion detection essential for improving survival rates and supporting clinical diagnosis. Although current pretrained models for predicting benign or malignant lesions achieve high accuracy, they often focus on…

Development of an efficient deep learning model for arrhythmia detection from consumer smartwatches (2026)

Frontiers in Artificial Intelligence Authors Dan-Cristian George, Mihai-Alexandru Hulubeac, Ştefan-Lucian Grămadă, Z. Bálint, L. Dioşan Abstract Cardiac arrhythmias often progress without clear symptoms and may remain undetected until severe complications occur. Continuous monitoring through consumer smartwatches offers a scalable and non-invasive opportunity for real-time rhythm screening in free-living conditions. However, wrist-based photoplethysmography (PPG) signals…

Machine learning prognostication in nasopharyngeal carcinoma: a european multicentre analysis of survival and risk of second malignancy (2026)

European Archives of Oto-Rhino-Laryngology Authors I. Pușcaș, Anda Gâta, P. Rizzo, M. Stellin, V. Rampinelli, D. Tomasini, C. Piazza, Daniele Borsetto, W. Ince, C. Chiesa-Estomba, Maria Landa-Garmendia, P. Surda, Eleanor J. Crossley, Matt Lechner, Teodora Maria Ursu, L. Cernau, Adél Bajcsi, Laura-Silvia Dioşan, C. Chira, Alexandra Roman, V. Gâta, Alexandru Irimie, Silviu Albu Abstract…

Assessing the Educational Benefits of Student-Developed Software for Citizen Science (2026)

International Conference on Computer Supported Education Authors L. Cernau, Simona Motogna, L. Diosan Abstract In the context of Community and Citizen Science (CCS) projects, communication and collaboration are essential, especially in interdisciplinary partnerships. However, existing research rarely examines these dynamics in student teams. This gap is particularly evident in computer science education, where CCS…

Generative AI in Computer Science Education: Insights from an Exploratory Study of Students, Educators, and Industry Professionals (2026)

International Conference on Computer Supported Education Authors L. Cernau, L. Diosan, Camelia Serban Abstract This study offers preliminary insights into the adoption of Generative Artificial Intelligence (GenAI) tools in computer science (CS) education, drawing on responses from 202 university-level computer science students, 16 educators, and 6 industry professionals. Employing a three-dimensional approach, the study…

Imitation Learning via Deep Q-Learning for Multi-robot Path Planning (2026)

Hybrid Artificial Intelligence Systems Authors Anikó Kopacz, Enol García González, Camelia Chira, José R. Villar Abstract Multi-robot path planning is essential for industrial operations, e.g., for manufacturing and warehouse logistics. Traditional path planning approaches may impose an unnecessary increase in computational demands when countered by unexpected events or failures. Thus, investigating machine learning approaches,…

A Granular Ball–Ant Colony Optimization Framework Enhanced by Variable Neighborhood Search for the Multi-Depot Half-Open Time-Dependent EVRP (2026)

Annual Conference on Genetic and Evolutionary Computation Authors Yingkai Xu, Anikó Kopacz, Camelia Chira Abstract The widespread adoption of electric vehicles (EVs) in urban logistics has led to the Electric Vehicle Routing Problem (EVRP) emerging as a prominent topic in combinatorial optimization research. To improve the efficiency of urban logistics distribution and minimize operational…