Makhmud Shaban

National Research University Higher School of Economics

Papers

Total Citations

H-Index

About

Makhmud Shaban is a researcher at the intersection of artificial intelligence, computer vision, and multimodal reasoning. His work centers on developing novel computational models that bridge visual perception and natural language understanding, with a particular focus on visual question answering (VQA) systems. Shaban's most notable contribution is the introduction of the "Vector Semiotic Model" for VQA, a framework that integrates semiotic theory with vector space representations to enable more nuanced and context-aware reasoning about images. This approach, detailed in his 2021 paper of the same name, has garnered 13 citations and represents a significant step toward more interpretable and robust AI systems. By combining insights from linguistics, semiotics, and deep learning, Shaban's work offers a fresh perspective on how machines can process and respond to complex visual queries. His research not only advances the technical capabilities of VQA models but also opens new avenues for exploring the role of symbolic reasoning in neural architectures. For students and researchers in AI, Shaban's work exemplifies the value of interdisciplinary thinking in tackling fundamental challenges of machine intelligence.