Gorjan Radevski

I am a Research Consultant with the Human-Centric AI group at NEC Labs Europe (since November 2023), where I work on topics related to Large Language Models (LLMs), specifically on improving their alignment, steering, reasoning, and interpretability. I led (ML and engineering) the LLM Explainer project, which won NEC’s Best Value Award globally in 2025, which was also published at ACL 2025. I completed my Ph.D. in 2024 at KU Leuven and continued as Postdoctoral Researcher at the VISICS lab within ESAT-PSI from June 2024 to October 2025, working with Prof. Tinne Tuytelaars.

My research focuses on Deep Learning with dual expertise in Natural Language Processing and Computer Vision, with special interest in multimodal learning involving images, text, videos, audio, and knowledge graphs. My work as a leading author (or equal contributor) has been published at top-tier venues including NeurIPS (×2), ACL, EMNLP (×2), CoNLL, ICCV, and BMVC.

In the past, I did Machine Learning internships at:

• NEC Labs Europe: Worked with Kiril Gashteovski, Carolin Lawrence, and Goran Glavas, leading to a publication at EMNLP 2023: Linking Surface Facts to Large-Scale Knowledge Graphs.

• IBM Research: Worked with Jasmina Bogojeska on medical applications of machine learning, resulting in a Journal of Infectious Diseases (2021) publication: Cohort-Derived Machine Learning Models for Individual Prediction of Chronic Kidney Disease in People Living with HIV.

• Luminovo: Contributed to industry-focused Computer Vision solutions.

In the past, I graduated Cum Laude with a Master in Artificial Intelligence from KU Leuven in 2019, after earning my Bachelor’s degree in Computer Science from the University of Ss. Cyril and Methodius in North Macedonia in 2017.