Category: Research

Posted on

Conference Paper: Real-time Image Generation on ARM-based Edge Devices

We are pleased to share that researchers from the University of Donja Gorica (UDG) presented their latest work at the 2025 IEEE International Symposium on Applied Sciences (ISAS). The paper, titled “Real-time Image Generation Utilizing ARM SBC Architecture”, is now published by IEEE and available at the following [link].

Click on image to open

The paper, authored by Igor Ćulafić, Tomo Popović, Ivan Jovović, and Stevan Ćakić, explores the deployment of advanced generative AI models on ARM-based edge devices, specifically the NVIDIA Jetson Orin Nano platform. Traditionally, real-time image generation with models such as Stable Diffusion has required powerful desktop GPUs or HPC clusters. This research demonstrates that, through careful CUDA optimization, ARM compatibility adjustments, and dynamic resource management, real-time performance of 2–6 FPS at 512×512 resolution can be achieved directly on low-power edge hardware.

The work addresses thermal management, memory constraints, and software compatibility challenges, proposing a custom ARM-optimized Docker environment and adaptive workload balancing. The results show how decentralized, low-power edge devices can complement high-performance computing ecosystems, opening new opportunities in fields such as healthcare, automotive, and smart city applications.

This publication also reflects the mission of NCC Montenegro to support academia and young researchers in advancing AI and HPC knowledge. By providing expertise, resources, and collaboration opportunities, NCC Montenegro helps integrate cutting-edge research with the broader European HPC ecosystem.

Posted on

Support to young researchers from the Faculty of Electrical Engineering

The NCC Montenegro team at the University of Montenegro (UoM) regularly meets and collaborates with various research groups within the university. In this way, they stay updated on new research projects, emerging research directions, and especially the topics pursued by young researchers. As a result, the need for high-performance computing (HPC) resources has been identified for the master’s research conducted by two research assistants at the Faculty of Electrical Engineering, UoM, led by Assistant professor Miloš Brajović.

Their research deals with Graph Neural Networks (GNNs), with a particular focus on data representation, interpretability and scalability for complex scientific datasets. GNNs have demonstrated remarkable potential in modeling relational and structured data across various domains, including physics, chemistry, biology and computer vision. However, despite their predictive power, their “black-box” nature poses challenges in terms of explainability and trustworthiness, especially in critical applications such as scientific discovery and engineering.

Successful submission for EuroHPC call

To benchmarking state-of-the-art GNN architectures, evaluate their performance and scalability, and develop and test new GNN models and interpretability techniques for graph-based applications, these two researchers will require access to HPC resources. Therefore, the NCC Montenegro team supported them in preparing and submitting an application for the Development call to gain access to the Leonardo HPC. As a result, they got access to the Leonardo Booster partition, securing 4,500 node hours for their research.

Posted on

Collaboration with NVIDIA, OpenACC and six NCCs

In collaboration with NVIDIA and the OpenACC organization, a group of National Competence Centers from Austria, Czechia, Germany, Montenegro, Poland, Slovenia, and Sweden organized several Bootcamps for the European HPC and AI user community.

Students, researchers from UDG and UoM, enthusiasts, and industry experts in the fields of high-performance computing and artificial intelligence, together with hundreds of participants from across Europe, attended courses on parallel programming (N-Ways-GPU and Multi-GPU) and AI (AI for Science and AI Profiling). Researchers from Montenegro also contributed as teaching assistants.

As one of the events of this collaboration, we are pleased to announce the OpenAI Hackathon, which will take place from October 14 to 23, 2025. The event is led by NVIDIA and the OpenACC, together with the EuroCC National Competence Centres of Austria, Germany, and Poland.  Open AI Hackathons are multi-day, intensive hands-on events designed to help AI and ML engineers and data scientists accelerate, optimize, and scale their real-world projects leveraging the latest technologies. The event pairs participating teams with dedicated expert mentors to enhance the performance, efficiency, and scalability of their applications using state-of-the-art programming models, libraries, and tools. Whether you’re working on deep learning, data analytics, or model optimization, this hackathon provides a unique opportunity to push the boundaries of innovation using an advanced AI and ML infrastructure.

Important dates

  • 05 August 2025 – Application Deadline
  • Aug/Sep 2025 – Notification about Acceptance
  • 14.–23.10.2025, 09:00 – 17:00 CEST, Hackathon ONLINE (using Zoom)

More info, agenda and registration at LINK.

Posted on

Master Thesis Defense: Development of Edge/AI Applications with HPC Support

Mr. Elvis Taruh successfully defended his master’s thesis titled “Development of Edge/AI Applications with HPC” at the Faculty of Information Systems and Technologies, University of Donja Gorica.

Mr Elvis Taruh

ABSTRACT – The efficiency of training artificial intelligence (AI) models has become a crucial factor in modern research, especially when dealing with complex systems that require substanial computational power. This study explores how the application of high-performance computing (HPC) and Edge devices can optimize the AI model training process, reducing processing time and improving efficiency. Through an experimental approach, AI model training was analyzed across three different platforms. Local computer, Google Colab and the HPC cluster at the University of Donja Gorica. As a practical example, livestock detection was used. By comparing the training time, memory consumption, and model accuracy, the research demonstrates that HPC clusters significantly accelerate the training process compared to traditional methods, while Edge devices enable faster real-time data analysis.

There was around 30 people attending. This was a small celebration for EuroCC2 and EuroCC4SEE projects
Posted on

Master Thesis Defense: AI Tutors with LLMs and HPC

Mr. Arnad Lekić successfully defended his master’s thesis titled “Development of an AI Tutor Using Large Language Models and HPC” at the Faculty of Information Systems and Technologies, University of Donja Gorica.

Mr Arnad Lekic

ABSTRACT – This thesis explores the development of a personalized AI tutor using large language models (LLMs), with a specific focus on the LLaMA architecture and the application of High-Performance Computing (HPC) resources. The research involves the acquisition, setup, and evaluation of an open-source LLaMA model, with the goal of building a system capable of automated test grading. Special emphasis is placed on the training efficiency and feasibility of running the model locally using the available computing nodes, compared to cloud-based solutions like Google Colab. Beyond the technical implementation, the study also addresses the ethical challenges of using generative AI in education. Through experimental analysis, the research demonstrates that open models can be effectively adapted for educational purposes, with the potential to expand to grading diverse exam formats and generating educational content. The work provides directions for future development of systems leveraging advanced multimodal models for more complex tasks.

The defence was attended by over 30 people. We had three candidates that day, all in the context of EuroCC2 and EuroCC4SEE
Posted on

Master Thesis Defense: HPC and AI for Education Enhancement

Ms. Enisa Trubljanin successfully defended her master’s thesis titled “Deep Learning with Application in Education” at the Faculty of Information Systems and Technologies, University of Donja Gorica. The development and testing of these solutions were supported by high-performance computing (HPC) resources provided through the EuroCC initiative in Montenegro.

Ms. Enisa Trubljanin

ABSTRACT – This master’s thesis explores the potential application of deep learning in education through the development and evaluation of two concrete solutions: an intelligent chatbot for solving matrix problems and a model for detecting cheating during online exams by analyzing eye movement. The first part of the thesis provides a theoretical foundation of deep learning, with a focus on neural networks, their architectures, transfer learning, and evaluation metrics. The practical part presents the development of a chatbot based on advanced language and mathematical models, implemented using high-performance computing cluster resources, enabling students to engage in interactive mathematics learning. Additionally, a model for detecting cheating through gaze analysis was developed, trained on the Columbia Gaze Dataset, and integrated into an online exam proctoring system. Evaluation results demonstrate a high level of accuracy and user satisfaction for both solutions. Beyond the technical aspects, the thesis also addresses ethical issues and privacy concerns related to the use of artificial intelligence in educational settings. Based on the findings, the study highlights the broad range of potential applications of deep learning in modern educational systems.

There was three great candidates on the same day!
Posted on

Two Montenegrin SMEs Secure EuroHPC Access for AI-Powered HR

We are pleased to announce that two Montenegrin SMEs, Recrewty and DigitalSmart, have been awarded access to the Leonardo Booster at CINECA, one of Europe’s most powerful high-performance computing (HPC) systems. The access is granted under the EuroHPC JU Development Call, providing 12 months of HPC resources to support advanced AI development and innovation.

The awarded project, HPC4HR – High-Performance Computing for Human Resources, aims to revolutionize recruitment processes in the Western Balkans through the integration of generative AI (GenAI) and HPC technologies. The project focuses on analyzing multimodal data—text, audio, and video—from candidate applications to enable efficient, unbiased, and culturally sensitive hiring processes. The HPC resources will be used in support to their joint FFPlus project GenAI-HPC4WB (link).

The GenAI-HPC4WB project combines GenAI, ML, and HPC to optimize hiring processes and enhance business culture in the Balkan region

To achieve this, the project will leverage cutting-edge AI models such as LLaMA 3.x, Mistral, Wav2Vec 2.x, Whisper, FaceNet, and DeepFace, all fine-tuned using HPC resources at CINECA. These models will be developed to evaluate resumes, analyze psychometric traits from audio recordings, and interpret emotional and behavioral cues from HR data. By utilizing HPC, the project ensures scalability and processing speed, enabling large datasets to be handled efficiently, significantly shortening recruitment cycles and improving candidate matching. In addition to enhancing operational efficiency, HPC4HR emphasizes ethical AI development, aiming to reduce biases in recruitment and promote diversity and inclusion. The expected outcomes include a set of adaptable, high-performance AI tools that set new standards for digital transformation in human resources, applicable across industries and geographies.

Leonardo Booster partition will be used in this project

The success of Recrewty and DigitalSmart reflects the growing impact of NCC Montenegro in strengthening the national HPC and AI ecosystem. By supporting companies in accessing leading European HPC infrastructure, NCC Montenegro continues to drive digital innovation, competitiveness, and technological excellence in the region.

Privacy Policy Proudly powered by WordPress