Projects
LLM-powered assistant for creating, editing, and interpreting business process diagrams.
4-bit quantized and fine-tuned TinyLlama model for e-commerce intent detection.
AI prototype for mapping traffic signs and street infrastructure from 360° video.
AI prototype using YOLOv11 OBB to detect dry stone walls in LiDAR imagery.
A computer vision system that uses satellite and drone imagery to detect buildings, land usage, and illegal waste disposal sites.
Developed an app leveraging GPT-4 vision capabilities and OCR services to digitize pricelist images.
Industrial Defect Detection Prototype
AI prototype for an NDA-protected client, designed to detect defects in high-resolution industrial imagery.
A fine-tuned version of FLAN-T5-large model trained on the Winograd WSC dataset for coreference resolution tasks.
An application to convert textual process descriptions into simplified BPMN diagrams using NLP.
A BERT model extracting actors, activities, activity details, process context, and business rules from process descriptions.
A Streamlit app showcasing a custom spaCy model trained to identify tasks in business process descriptions.
Publications
BPMN Assistant: An LLM-Based Approach to Business Process Modeling
Licardo, J.T., Tanković, N., Etinger, D.
arXiv preprint (2025)
From Innovation to Impact: Case Studies of EDIH Adria TBI Projects
Lorencin, I., Krčelić, G., Blašković, L., Žužić, A., Licardo, J.T., Babić, S., Etinger, D., Tanković, N.
48th ICT and Electronics Convention MIPRO (2025)
Intelligent Robotics—A Systematic Review of Emerging Technologies and Trends
Licardo, J.T., Domjan, M., Orehovački, T.
Electronics (2024)
A Method for Extracting BPMN Models from Textual Descriptions Using Natural Language Processing
Licardo, J.T., Tanković, N., Etinger, D.
Procedia Computer Science (2024)