Student Research Associate
Smile Care Current
[ Open to research & job opportunities]
S M NafimNiloy
[Researcher · Software Engineer]
Computer Science and Engineering undergraduate with research experience in graph neural networks, computer vision, medical imaging, and natural language processing, seeking opportunities to apply machine learning and software engineering skills in a professional setting. Experienced in end-to-end ML pipelines, full-stack development, and reproducible experimentation.
- Graph Neural Networks
- Medical Imaging
- Bengali NLP
- Computer Vision
- Large Language Models
- Retrieval-Augmented Generation
- Explainable AI
[01 — Experience]
Where I work
[02 — Education]
Where I studied
- University
American International University-Bangladesh
Bachelor of Science in Computer Science and Engineering
- Higher Secondary
Dhaka College
Higher Secondary Certificate
[03 — Research]
Research & publications
Do Heterogeneous Graph Neural Networks Improve Cross-Cohort Glioma Grading? A TCGA-CGGA Benchmark with Graph Ablation and Explainability
Under review at NetMAHIB
Benchmarking heterogeneous graph neural networks against tabular baselines for cross-cohort glioma grading across TCGA and CGGA genomic datasets, with graph ablation and explainability analysis.
Papers 1
Commuting Pattern and Challenges Among Students in Dhaka City: An Analysis for Sustainable Urban Mobility
In progress 4
Do Heterogeneous Graph Neural Networks Improve Cross-Cohort Glioma Grading? A TCGA-CGGA Benchmark with Graph Ablation and Explainability
Heterogeneous Lesion Graph Network for Diabetic Retinopathy Grading: An Exploratory Study of Spatial Lesion Interaction Modeling
Explainable Machine Learning of Texture Signatures in Pancreatic Cancer via Leakage-Safe Radiomics and Rule Mining
TeaBD-HybridNet: Maximizing Pretrained Knowledge Transfer in a Dual-Branch CNN-ViT Architecture for Tea Leaf Disease Classification
[04 — Projects]
Things I've built
BanglaLLM
A demo version of a 7B model. Developed and trained a 100M-parameter decoder-only language model for Bangla using a custom 16K-vocabulary tokenizer, with training and inference implemented in Python and Transformers.
Animal Image Classification with ResNet50
Built and fine-tuned a ResNet50 model to classify images of 10 animal species, reaching 96.59% validation accuracy through transfer learning, data augmentation, and hyper-parameter tuning. A Streamlit app lets you upload an image and get a prediction instantly.
EduTutor BD
End-to-end RAG-based AI tutoring system for SSC students using OCR-processed Bengali textbooks, LangChain, and FastAPI, with retrieval-grounded answers and student progress tracking.
Stock Prediction Portal
Full-stack stock prediction platform built with Django, React, and Bootstrap, integrating machine learning models for historical market-data analysis, trend prediction, and interactive visualization.
Smart Cafe
Web application built from scratch in PHP and MySQL following an MVC architecture, with role-based dashboards for Admin, Manager, and Customer and full CRUD for menus, inventory, and customer preferences.
[05 — Code]
Recent code
building_blockchain_in_rust
Building bitcoin in rust
NafimPortfolio
Personal Portfolio of S M Nafim Niloy
rust_n_nvim_practice
Trying to get into the cult
assets
Holds different assents for the personal projects
tcga-cgga-thesis
No description yet.
TeaLeaf-Disease-Classifier
CNN-ViT hybrid for tea leaf disease classification.
[06 — Skills]
Skills & toolkit
- Languages
- Frameworks
- ML / AI
- Databases
- Tools
- Libraries