Gorjan Radevski

prof_pic.jpg

I am a Research Consultant with the Human-Centric AI group at NEC Labs Europe (since November 2023), where I work on topics such as Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), reasoning, and LLM agents.

I completed my Ph.D. in 2024 at KU Leuven and continued as a full-time Postdoctoral Researcher at the VISICS lab within ESAT-PSI from June 2024 to March 2025, working with Prof. Tinne Tuytelaars. I now hold a part-time postdoctoral position at VISICS. My research focuses on Deep Learning and its applications in Natural Language Processing and Computer Vision, with interests in multimodal learning involving images, text, videos, audio, and knowledge graphs, as well as weakly-supervised learning and (egocentric) video understanding.

In the past, I did Machine Learning research internships at:

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.

selected publications

  1. NeurIPS
    LaSCal: Label-Shift Calibration without target labels
    Teodora Popordanoska*Gorjan Radevski*, Tinne Tuytelaars, and 1 more author
    In The Thirty-eighth Annual Conference on Neural Information Processing Systems, 2024
  2. EMNLP
    Linking Surface Facts to Large-Scale Knowledge Graphs
    Gorjan Radevski, Kiril Gashteovski, Chia-Chien Hung, and 2 more authors
    In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, 2023
  3. ICCV
    Multimodal Distillation for Egocentric Action Recognition
    Gorjan Radevski*, Dusan Grujicic*, Matthew Blaschko, and 2 more authors
    In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), Oct 2023
  4. BMVC
    Revisiting Spatio-Temporal Layouts for Compositional Action Recognition
    Gorjan Radevski, Marie-Francine Moens, and Tinne Tuytelaars
    Proceedings BMVC 2021, Oct 2021