PhD work on Vision-Language Models, Vision Transformers, and Large Language Models at the JD-ICE European doctorate. Earlier research on semi-supervised learning published in IEEE and Springer.
Research on Vision-Language Models (VLM), Vision Transformers (ViT), and Large Language Models (LLM) — with emphasis on hardware-aware inference, precision trade-offs, and real-time edge deployment for resource-constrained environments.
Semi-supervised decision trees with distance-based sample weighting — reference implementation of the Semi-CART paper (Springer IJMLC 2024, 29 citations).
Distance-based sample weights for semi-supervised deep learning, implementing the method from the IEEE ICMLT 2025 oral presentation.