All research areas
Research
Artificial Intelligence
Applied AI systems built to survive contact with production.
We are interested in AI that ships. That means evaluation before deployment, a measurable baseline, and a clear account of how the system fails. A demo that works once is not a result.
In production
CMS — plagiarism & similarity screening
ML-backed similarity checks run inside CMS's submission pipeline — applied model work living in a product, not a notebook.
See the product →What this looks like in practice
- Model selection, fine-tuning, and evaluation harnesses
- Retrieval-augmented generation over private corpora
- Agentic workflows and tool-use architectures
- Inference optimisation and cost modelling
- Human-in-the-loop review and guardrails
Related publications
- Hybrid Retrieval-Augmented Framework for Low-Resource Bangla Visual Question AnsweringMd Mahmudul Hoque · 2 September 2026
- Deep Vision for Rail Safety: Real-Time Object Detection at Level CrossingsMd Mahmudul Hoque · 2 September 2026
- HybridADNet: A Multi-Paradigm Deep Learning Framework for Alzheimer's Disease Diagnosis from Brain MRIMd Mahmudul Hoque, Md Kawser Islam, Ohidujjaman, Abdullah Rakib Akand, Mahmudul Hasan · 2 September 2026
- HybridVirusNet: A Hybrid Detection–Classification Framework for Multi-Class Virus Identification in TEM ImagesMd Mahmudul Hoque · 2 September 2026
- HyConDViT-Net: A Vision-Based Hybrid Deep Learning Approach Integrating CNNs, Vision Transformers, and Detection Backbones for PCOS Detection from Ultrasound ImagingMd Kawser Islam, Md Mahmudul Hoque, Md. Saiful Islam, Md. Sourav Talukder, Abdullah Rakib Akand, Mahmudul Hasan · 2 September 2026
- Why the n mattersMd Mahmudul Hoque · 17 July 2026