Md. Mahmudul Hasan

Md. Mahmudul Hasan

CSE Undergraduate, University of Dhaka

Hi, there!

Welcome to Md. Mahmudul Hasan's website! I am a senior undergraduate student in Computer Science and Engineering at the University of Dhaka, where I have focused on developing a strong foundation in both theoretical and applied principles.

I am deeply interested in the recent advancements of Artificial Intelligence, which have led me to pursue research in this field. Currently, I work as an Undergraduate Research Assistant at the Cognitive Agents and Interaction Lab (CAIL) under the supervision of Dr. Md. Mosaddek Khan. My research interests broadly include:

  • Machine Learning (ML)
  • Large Language Models (LLMs)
  • Vision-Language Models (VLMs)
  • Multimodal Learning

Beyond research, I have a strong passion for algorithmic problem solving and devoted much of my early undergraduate years to competitive programming. I have also aimed to build a solid understanding of software engineering through various academic projects.

Looking ahead, I hope to engage in innovative research projects that challenge my abilities and allow me to contribute meaningfully to the field.

I'm expected to graduate before Jan 2026 and am currently on the job market (for both academic and industrial opportunities). I would greatly appreciate it if you could email me about any available opportunities!

News

  • Sep 2025: Our paper GraDeT-HTR is accepted at EMNLP 2025 System Demonstrations! Check out the paper and code.

  • Jun 2025: We’ve released our new work GraDeT-HTR, now freely available for public use! Visit our site.

Publications

EMNLP 2025 Demo
sym

GraDeT-HTR: A Resource-Efficient Bengali Handwritten Text Recognition System utilizing Grapheme-based Tokenizer and Decoder-only Transformer

Md. Mahmudul Hasan, Ahmed Nesar Tahsin Choudhury, Mahmudul Hasan, Md. Mosaddek Khan

  • Utilizes a decoder-only architecture for Bengali handwritten text recognition without any pretrained LM.
  • Employs a grapheme-based tokenizer, which significantly boosts recognition accuracy.
[paper] [code] [abstract]

Educations

  • 2022 – 2026 (expected)
    B.Sc. in Computer Science & Engineering, University of Dhaka

Research Experience

  • Jan 2024 – Present
    Undergraduate Research Assistant
    Cognitive Agents and Interaction Lab (CAIL), University of Dhaka
    Working under the supervision of Dr. Md. Mosaddek Khan

Teaching Experience

  • Jan 2022 – Jun 2023
    Physics Instructor
    Udvash-উদ্ভাস, Dhaka, Bangladesh
    Taught Physics to high school students (Grades 9–12)

Projects

  • Oct 2024 – Jan 2025, Flash: Fastest-Way-to-Learn
    Built an end-to-end video summarization system using multimodal deep learning.
    Developed a fully functional course-selling platform with Spring Boot, Next.js, and PyTorch.

  • Apr 2024, ConvoCorner
    Designed a real-time messaging app with text and image support using WebSockets.
    Implemented the TCP/IP protocol from scratch to ensure reliable data transmission.

  • Sep 2023 – Nov 2023, KodeShell
    Created an Android app for aggregating contest schedules and user statistics across competitive programming platforms.
    Added community features such as posts, user search, and messaging.

  • Feb 2023 – May 2023, SmartAcademicManager
    Developed a desktop application for managing academic resources, schedules, tasks, and course attendance.
    Designed a modern JavaFX interface for streamlined academic management.

  • Oct 2022 – Dec 2022, Cannon Fight
    Built a 2D projectile-based shooting game in C/C++ using SDL2, featuring both single-player and multiplayer modes.