Hi, there!
Iām Meheraj Hossain, a CSE graduate from the University of Dhaka, Bangladesh. I am currently working as a Machine Learning Engineer II at Therap (BD) Ltd, a US-based software company operating in Bangladesh. My role involves developing applications leveraging computer-vision models and tools to enhance medical care.
I am also involved as a Part-time Research Assistant at the Center for Computational & Data Sciences (CCDS) where my works are supervised by Dr. Amin Ahsan Ali. Here, my current research focuses on utilizing Large Language Models (LLMs) for low-resource languages, particularly Bangla, to improve language understanding and generation in these underrepresented languages.
My research interests lie broadly in the area of Natural Language Processing and Computer Vision, with a focus on low-resource domains. Specifically, I am interested in:
- Low-Resource NLP: Enhancing low-resource languages by leveraging cross-lingual data from high-resource languages.
- Continual Learning: Developing strategies to prevent catastrophic forgetting when adapting LLMs to new domains.
- Multimodal Learning: Investigating how different modalities e.g., text and images interact and convey information across them.
- Applications of LLMs and VLMs: Exploring the diverse applications of large language models (LLMs) and vision-language models (VLMs) across various domains to enhance functionality and user experience.
I am actively seeking Ph.D. opportunities for Fall 2025.
News and Updates
- October 2024: Promoted to Machine Learning Engineer II at Therap (BD) Ltd.
- August 2024: Paper āHow Good are LM and LLMs in Bangla Newspaper Article Summarizationā, accepted at the 27th International Conference on Pattern Recognition, ICPR 2024.
- September 2023: Started working at Center for Computational & Data Sciences (CCDS) as Research Assistant(Part-Time).
- October 2022: Promoted to Machine Learning Engineer at Therap (BD) Ltd.
- September 2021: Started working at Therap (BD) Ltd. as Associate Machine Learning Engineer.
- August 2021: Defended undergraduate thesis.
Publications
Faria Sultana, Md Tahmid Hasan Fuad, Md Fahim, Rahat Rizvi Rahman, Meheraj Hossain, M Ashraful Amin, A K M Mahbubur Rahman, Amin Ahsan Ali, How Good are LM and LLMs in Bangla Newspaper Article Summarization, in the Proceedings of the 27th International Conference on Pattern Recognition, ICPR 2024, To Appear. [Paper]
Md Fahim, Meheraj Hossain, Sadman Rohan, Md Ashraful Amin, AKM Mahabubur Rahman, Amin Ahsan Ali, L-Context: Layer-wise Context Vectors for Better Text Classification Using Pre-trained Language Models, In Review. [Paper]
Patents
- David Lawrence Turock, Justin Mark Brockie, James Michael Kelly, Richard Allen Robbins, Meheraj Hossain, et al., Automated, Non-Invasive Artificial Intelligence Machine Learning Method and System for Identifying and Redacting Personally Identifiable Information in a Monitored Environment using Real-Time Sensor Data, US Patent Publication No. US 2024-0212804 A1, published June 27, 2024. (Status: Pending) [Patent]
Education
- Bachelor of Science (B.Sc.) in Computer Science and Engineering
- University of Dhaka (January 2017 ā August 2021)
- CGPA: 3.74 out of 4.00
- Merit Position: 7th out of 65 students
Technical Skills
- Programming Languages: Python, C, C++, Java, JavaScript
- Libraries: PyTorch, PyTorch-Lightning, TensorFlow, Keras, OpenCV, Scikit-learn, Numpy, Pandas, Matplotlib, Seaborn
- Frontend Development: HTML, CSS, Bootstrap, jQuery, Ajax
- Backend Development: Node.js, Express.js
- Database: MongoDB, SQL, SQLite
- Hardware Tools: Nvidia Jetson Xavier NX, Jetson AGX Orin, Jetson Orin Nano, Raspberry Pi
- Miscellaneous: Git, Docker, MATLAB, LaTeX, TensorRT
Awards & Achievements
Secured 5th Position in Apurba Presents Bhashabhrom: Bangla Grammatical Error Detection Challenge Datathon 2023 (Team: Team Aambella). [Link]
Selected as Finalist in Robi Datathon 2.0 (Team: The_Anomalies). [Link]
Awarded University Merit Scholarship by the Government of Bangladesh for outstanding academic performance.
Extracurricular Activities
- Competitive Programming
- Solved 1000+ problems on platforms like Codeforces (Max Rating: 1527), LightOJ, and UVA.
- Participated in several national and international programming contests during undergraduate studies.
- Kaggle Competitions
- Participated in several Kaggle competitions, including Google Brain Ventilator Pressure Prediction (Time Series Analysis) and Global Wheat Detection (Computer Vision Challenge).