HPC Montenegro - National Competence Centre for High-Performance Computing

24.10.2026.

MSc Thesis Defence: Generating and Evaluating Exam Questions Using LLMs and HPC

On October 21, 2026, MSc candidate Sara Kovačević successfully defended her thesis entitled “Generation and Quality Evaluation of Exam Questions Using Large Language Models and HPC Infrastructure” within the Artificial Intelligence Master’s programme at the Faculty of Information Systems and Technologies, University of Donja Gorica (UDG). The thesis was supervised by Prof. Dr. Tomo Popović. The research was partially supported by NCC Montenegro within the EuroCC3 project, including access to HPC infrastructure and support for experimental work. The study demonstrates the potential of combining generative AI and high-performance computing to support the preparation and evaluation of educational materials, with particular attention to the Montenegrin language.

Ms Sara Kovacevic at her MSc thesis defence

ABSTRACT – This thesis presents the development and evaluation of an automated system for generating exam questions from video lectures using large language models (LLMs). The system integrates automatic transcription, extraction of key concepts, generation of multiple-choice and short-answer questions, and automated quality assessment. Nine LLM configurations were evaluated in English and Montenegrin, using local computing resources, the UDG HPC cluster, and API-based inference services.

The evaluation combined linguistic and structural metrics, Bloom’s taxonomy, and an LLM-as-Judge approach to assess the quality of generated questions. Experimental results highlighted challenges faced by smaller models when generating educational content in Montenegrin, while larger models achieved more consistent results. Experiments on the UDG HPC cluster demonstrated a 17.9× GPU speedup compared with CPU inference for the same model.

The research highlights the potential of AI and HPC technologies to assist educators in preparing assessment materials, while emphasizing the importance of human review and further pedagogical validation before practical deployment.

24.10.2026.24.10.2026.

MSc Thesis Defence: Explainable AI for Type 2 Diabetes Risk Assessment

On October 21, 2026, MSc candidate Sanja Lazić successfully defended her thesis entitled “Interpretable Machine Learning and Deep Learning Models for Type 2 Diabetes Risk Prediction Based on Behavioural and Clinical Indicators” within the Artificial Intelligence Master’s programme at the University of Donja Gorica, Faculty for Information Systems and Technologies, under the mentorship of Prof. Dr. Tomo Popović.

The research and experimental work were partially supported by NCC Montenegro through HPC infrastructure and expertise within the EuroCC3 project, with additional research support from the AI-AGE project. Through its involvement in academic research, mentoring, and competence development, NCC Montenegro contributes to strengthening the application of advanced AI and HPC technologies in healthcare and other scientific domains.

Ms Sanja Lazić during her MSc thesis defence

The thesis investigates the application of machine learning, deep learning, and explainable AI techniques to type 2 diabetes risk assessment, focusing on predictive performance, reliability, and interpretability. The research also demonstrates how AI models can support preventive healthcare through accessible, questionnaire-based risk assessment without requiring laboratory measurements.

ABSTRACT – This thesis presents the development and systematic evaluation of machine learning and deep learning models for type 2 diabetes risk assessment using behavioural, clinical, and demographic indicators. The study analysed 253,680 records and compared five models: Logistic Regression, Random Forest, XGBoost, LightGBM, and a deep neural network. Model performance was evaluated in terms of discrimination, probability calibration, and interpretability. While the deep neural network achieved the highest ROC-AUC (0.7728), LightGBM demonstrated the most balanced overall performance. Explainable AI methods, including TreeSHAP, Integrated Gradients, and DeepLIFT SHAP, were applied to identify factors contributing to model predictions. A prototype web application was developed to demonstrate how estimated risks and their explanations could be presented to users.

The results demonstrate the potential of explainable AI for supporting non-invasive risk assessment and preventive screening, while highlighting the importance of model reliability, transparency, and further validation before clinical application.

22.10.2026.24.10.2026.

UDG and FiveG Explore Further Collaboration in AR/VR, Generative AI and HPC

The University of Donja Gorica (UDG) hosted representatives of FiveG (Five Group) to discuss new opportunities for collaboration in augmented and virtual reality (AR/VR), generative artificial intelligence (AI), and high-performance computing (HPC).

FiveG has already successfully accessed EuroHPC resources with the support of NCC Montenegro through both Benchmark and Development calls for its Wasco AI project, utilizing the Leonardo Booster supercomputer. The meeting also addressed opportunities for further EuroHPC access applications to support the company’s ongoing AI development activities.

UDG hosted FiveG representatives to discuss further cooperation in AI, AR/VR and HPC

Building on an earlier initiative for cooperation between UDG and FiveG on establishing an AR/VR and AI laboratory, participants discussed the possibility of developing a demonstration setup for academia and industry. The proposed activities would showcase AR/VR applications and explore how generative AI and HPC resources could support the development of immersive digital content.

The meeting reaffirmed the shared interest in connecting academic research, education, and industry innovation through practical applications of emerging technologies.

Exploring new opportunities for AR/VR demonstrations, generative AI and EuroHPC resources

16.10.2026.16.10.2026.

HPC Montenegro and Morsko dobro Explore Opportunities for HPC and AI Cooperation

Initial consultations under EuroCC 3 strengthen engagement with major public enterprises and potential large-scale users of advanced computing technologies.

As part of its ongoing activities to engage large organizations and public-sector institutions, HPC Montenegro (NCC Montenegro) held an initial online meeting with representatives of the Public Enterprise for Coastal Zone Management of Montenegro (Morsko dobro) to explore opportunities for cooperation and the potential application of High-Performance Computing (HPC) and Artificial Intelligence (AI).

Online meeting between HPC Montenegro and Morsko dobro

During the meeting, the activities, services, and support opportunities offered by HPC Montenegro within the EuroCC 3 project were presented. The discussion focused on the potential benefits of advanced computing technologies for public enterprises managing complex operations, infrastructure, and significant amounts of data.

Given the responsibilities of Morsko dobro, possible areas for future cooperation include advanced data analysis, coastal and marine environmental monitoring, spatial data processing, and decision-support systems for sustainable coastal management. These opportunities could provide a basis for identifying concrete use cases and further technical consultations.

Possible areas for future cooperation were discussed in order to identify concrete use cases

This initial meeting represents another step in HPC Montenegro’s efforts to engage major public-sector organizations, promote the adoption of HPC and AI technologies, and facilitate access to European supercomputing resources and expertise through the EuroHPC ecosystem.

15.10.2026.15.10.2026.

NCC Montenegro and NCC Bosnia and Herzegovina Strengthen Cooperation in HPC and AI

Continued collaboration under EuroCC 3 focuses on industry and public sector engagement, healthcare applications, and sharing HPC expertise and resources

On October 14, 2026, representatives of HPC Montenegro (NCC Montenegro) met with colleagues from NCC Bosnia and Herzegovina at the Verlab Institute in Sarajevo to discuss the continuation and expansion of their cooperation within the EuroCC 3 project.

Representatives of NCC Montenegro and NCC Bosnia and Herzegovina during their meeting at the Verlab Institute

Building on collaboration established through the previous EuroCC4SEE project, including a joint workshop on AI and HPC applications in healthcare organized at the Faculty of Medicine in Montenegro and recent collaborative research supporting the pharmaceutical industry, the meeting focused on new opportunities for joint initiatives and broader stakeholder engagement.

The participants discussed several HPC and AI use cases, particularly in healthcare and medical research, where both NCCs have relevant experience. Special attention was given to sharing expertise, human resources, HPC infrastructure, and experiences in engaging and supporting industry partners and public sector institutions. The discussion also addressed the promotion of results achieved through previous cooperation and opportunities to jointly assist companies in accessing European supercomputing resources through EuroHPC Joint Undertaking (EuroHPC JU) access calls.

Discussion was focused on joint efforts and experience sharing aimed at industry engagement

The Verlab Institute also expressed its willingness to support research activities in Montenegro by facilitating connections with healthcare industry partners and exploring opportunities for access to relevant datasets.

The meeting reaffirmed the commitment of both NCCs to strengthening regional collaboration under EuroCC 3, sharing knowledge and resources, and supporting the wider adoption of HPC and AI technologies in academia, industry, and the public sector.

13.10.2026.24.10.2026.

EuroHPC-Supported Research Advances AI-Based Lecture Transcription for Montenegrin

Results from the Exams 4.0 Proof of Concept project, supported by the Innovation Fund of Montenegro and EuroHPC computing resources, were presented at the international SAMYRAD 2026 conference in Seville, Spain.

The paper “Whisper-Based Lecture Transcription for Montenegrin Higher Education with a Practical Evaluation” was presented at the Smart Algorithms & Models: Your Reach to Advanced Dialogues (SAMYRAD 2026) conference, held on 5–6 October 2026 in Seville, Spain.

Authored by Stevan Čakić, Tomo Popović, Srđan Krčo, and Igor Čulafić, the paper investigates the use of OpenAI Whisper models for automatic transcription of university lectures in Montenegrin, a language not directly supported by Whisper.

The study evaluated three Whisper model variants and three related South Slavic language settings using 30 university lectures covering nearly 38 hours of audio. The experimental work involved generating 4,860 transcripts, with large-scale processing performed on the LUMI EuroHPC supercomputer in Finland.

The results identified Whisper’s turbo variant as the most suitable among the tested models in terms of transcription consistency, evaluated text quality, and processing speed. The research also provided practical recommendations for processing lecture recordings in Montenegrin.

These findings have already been incorporated into a new lecture-transcription module developed within the Exams 4.0 platform, enabling lecturers to transform audio and video recordings into text that can support AI-assisted preparation of educational materials and examination questions.

This R&D effort was conducted as part of the Exams 4.0 Proof of Concept project, implemented by DigitalSmart in collaboration with the University of Donja Gorica and funded by the Innovation Fund of Montenegro.

HPC Montenegro (NCC Montenegro) supported the research team in securing access to EuroHPC computing resources through the EuroHPC JU Development Access programme (project ID: EHPC-DEV-2024D12-018). The computational experiments were performed on LUMI, hosted by CSC in Finland and the LUMI consortium.

This work demonstrates how access to European HPC infrastructure can support applied AI research, foster innovation in higher education, and contribute to the development of digital tools for smaller and underrepresented languages.

11.10.2026.11.10.2026.

AI Research on Premium Domain Name Recommendation Published in IEEE Access

A new scientific paper titled “Premium Domain Name Recommendation via Semantic Retrieval and Reranking of Fixed Aftermarket Inventories” has been published in the international journal IEEE Access. The research was conducted by Milutin Pavićević, Tomo Popović, Srđan Krčo, and Miodrag Vujković from the University of Donja Gorica (UDG) and DunavNET.

The study addresses the challenge of recommending relevant premium domain names from large collections of domains already available for resale. The researchers developed and evaluated an approach combining large language models (LLMs), semantic embeddings, vector search using FAISS, and different reranking strategies. Experiments were conducted on 30,000 domain names sampled from a collection of nearly 700,000 premium domains, with evaluations involving 22 industry experts and 180 students. The results demonstrated the potential of semantic retrieval to improve domain name recommendations while balancing relevance, diversity, and computational cost.

The research also has clear potential for industrial application. Alicorn, a Montenegro-based software company specializing in solutions for the domain name industry, is already developing AI-powered domain name recommendation technologies, including its Name Sentinel platform. The methods investigated in this study could contribute to further improving such solutions, particularly through more effective semantic search and recommendation of premium domains.

The research represents another example of research and innovation supported by European initiatives and connected with the activities of HPC Montenegro (NCC Montenegro), contributing to the development of AI expertise and stronger links between academia and industry.

Read the scientific paper: IEEE Access – DOI: 10.1109/ACCESS.2026.3740779