Research

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.

Joint Doctorate JD-ICE Nov 2025 – Present
UniGe (IT) · UC3M (ES) · QMUL (UK)

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.

VLM ViT LLM Edge Inference QLoRA FP16 / INT8
30+
citations
1
h-index
1
i10-index
IEEE ICMLT 2025 · oral · Helsinki
Published in IEEE Xplore. Co-authors: S. Tabakhi, V. Seydi. 2025 ICMLT.
Springer IJMLC 2024 · 29 citations
International Journal of Machine Learning and Cybernetics, Vol. 15(10), pp. 4493–4510. Co-author: V. Seydi. Reference implementation: SemiCART.
View on Google Scholar ↗