Mikel Williams Lekuona
AI engineer · from research to production · PhD in multimodal AI
Image Complexity-Aware Adaptive Retrieval for Efficient Vision-Language Models
ECIR 2026
Paper
FiCo-ITR: bridging fine-grained and coarse-grained image-text retrieval for comparative performance analysis
IJMIR 2025
Paper
A Framework for Enabling Unpaired Multi-Modal Learning for Deep Cross-Modal Hashing Retrieval
J. Imaging 2022
Paper
I am a Research Associate in Software Engineering and Artificial Intelligence at Loughborough University, with a PhD in multimodal AI and first-author research on image-text retrieval. My work spans production LLM integration, hybrid semantic search, and evaluation methods that keep machine outputs grounded and auditable. I specialise in turning research prototypes into deployed, production-grade platforms.