Profile photo

Foysal Imtiaz Sabab

CS Graduate · AI Research · Full Stack

RESEARCH INTERESTS

Fields: Machine Learning, Natural Language Processing, Explainable AI, Generative AI

Topics: Large Language Models, Hallucination Detection and Mitigation, AI Reliability and Safety, Natural Language Inference, Low-Resource Language Processing, Trustworthy AI Systems

RESEARCH EXPERIENCE

Undergraduate Research

Feni University   ·   Sep 2025 – Mar 2026

Thesis: An Empirical Analysis of Hallucination Evaluation Metrics in Bangla using LLMs

  • Designed and executed an empirical evaluation framework to assess the logical and semantic stability of Generative AI models including Gemini 2.5 Flash, Gemma 3, and LLaMA 3.2. Investigated hallucination behavior and model reliability using Natural Language Inference (NLI), Named Entity Recognition (NER), and consistency-based evaluation on the BanglaQA dataset. Focused on trustworthiness in low-resource language settings and contributed toward building more reliable and interpretable LLM evaluation baselines. Led a 3-member undergraduate thesis team, coordinated methodology design, experimental workflow, and technical reporting with faculty supervision.

EDUCATION

B.Sc in Computer Science and Engineering    (CGPA: 3.63 / 4.0)

Feni University   ·   Jan 2022 – Mar 2026

Coursework: Artificial Intelligence, Pattern Recognition, Data Structures, Algorithms, OS, DBMS, Networking

PROJECTS

CV Analyzer

GitHub  ·  Live Demo

  • Developed a serverless AI-powered resume analyzer using ReactJS, React Router V7, TypeScript, and TailwindCSS. Integrated Puter.js to directly access cloud storage, AI, and database capabilities from the frontend without building a separate backend. Focused on clean user interaction, responsive UI, and lightweight AI-assisted resume evaluation workflow.

Facial Recognition System

GitHub

  • Built a real-time facial recognition and user authentication system using Python and OpenCV. Implemented webcam-based image acquisition, face enrollment, identity verification, image preprocessing, and authentication event logging. Added GUI-based interaction to improve usability and system accessibility.

SKILLS SUMMARY

Programming: Python, C++, JavaScript, TypeScript

Machine Learning & AI: Machine Learning, Deep Learning, LLMs, NLP, Model Evaluation

Data & Computing: NumPy, Pandas, Matplotlib, Seaborn, Scikit-learn, Data Preprocessing, EDA

Development & Tools: MERN Stack, Git, PostgreSQL, Linux, Jupyter Notebook

REFERENCE

Md Ismail Siddiqi Emon

PhD Candidate, Morgan State University

Machine Learning Associate, NIST, USA

mdemo1@morgan.edu