MD Mofijul Islam

Collaborator, AI/ML Wing

Applied Scientist II, AWS GenAI Innovation Center

Website

About

Researching on LLMs, Multimodal LLM, and Generative AI to tackle impactful real-world challenges.

Publications (5)

Abu Tyeb Azad, Fahim Ahmed, Ishita Sur Apan, Ezharuddin Jubaer, Sumaiya Karim Katha, Armun Alam, Amin Ahsan Ali, Aman Chadha, Md Mofijul Islam, AKM Mahbubur Rahman

Khondo: A Multimodal Benchmark for Document Packet Splitting of Bangla Forms

arXiv (Cornell University), 2026

Preprint / Working PaperDOI

Abu Tyeb Azad, Ishita Sur Apan, Fahim Ahmed, Sumaiya Karim Katha, Ezharuddin Jubaer, Armun Alam, Pranjal Kumar Nandi, Amin Ahsan Ali, Aman Chadha, Md Mofijul Islam, AKM Mahbubur Rahman

BaFCo: A Document Understanding Benchmark for Complex Bangla Form Comprehension

Computer Vision – ECCV 2026, pp. 402-420, 2026

Book ChapterDOI

Md Akil Raihan Iftee, Mir Sazzat Hossain, Rakibul Hasan Rajib, Tariq Iqbal, Md Mofijul Islam, M Ashraful Amin, Amin Ahsan Ali, AKM Rahman

SloMo-Fast: Slow-Momentum and Fast-Adaptive Teachers for Source-Free Continual Test-Time Adaptation

arXiv (Cornell University), 2025

Preprint / Working PaperDOI

Md Mubtasim Ahasan, Rafat Hasan Khan, Tasnim Mohiuddin, Aman Chadha, Tariq Iqbal, M Ashraful Amin, Amin Ahsan Ali, Md Mofijul Islam, AKM Mahbubur Rahman

FuseCodec: Semantic-Contextual Fusion and Supervision for Neural Codecs

arXiv (Cornell University), 2025

Preprint / Working PaperDOI URL

Md Mubtasim Ahasan, Md Fahim, Tasnim Mohiuddin, AKM Rahman, Aman Chadha, Tariq Iqbal, M Ashraful Amin, Md Mofijul Islam, Amin Ahsan Ali

Dm-codec: Distilling multimodal representations for speech tokenization

arXiv preprint arXiv:2410.15017, pp. 25580-25602, 2024

Journal ArticleDOI URL

Abu Tyeb Azad, Fahim Ahmed, Ishita Sur Apan, Ezharuddin Jubaer, Sumaiya Karim Katha, Armun Alam, Amin Ahsan Ali, Aman Chadha, Md Mofijul Islam, AKM Mahbubur Rahman

Khondo: A Multimodal Benchmark for Document Packet Splitting of Bangla Forms

arXiv (Cornell University), 2026

Preprint / Working PaperDOI

multimodal benchmark
vision-language models
document segmentation
document clustering
administrative documents

Abu Tyeb Azad, Ishita Sur Apan, Fahim Ahmed, Sumaiya Karim Katha, Ezharuddin Jubaer, Armun Alam, Pranjal Kumar Nandi, Amin Ahsan Ali, Aman Chadha, Md Mofijul Islam, AKM Mahbubur Rahman

BaFCo: A Document Understanding Benchmark for Complex Bangla Form Comprehension

Computer Vision – ECCV 2026, pp. 402-420, 2026

Book ChapterDOI URL

key information extraction
multimodal large language models
document layout analysis
government forms
chain-of-thought prompting
low-resource languages
zero-shot prompting
document understanding
Bengali language
annotated dataset

Md Akil Raihan Iftee, Mir Sazzat Hossain, Rakibul Hasan Rajib, Tariq Iqbal, Md Mofijul Islam, M Ashraful Amin, Amin Ahsan Ali, AKM Rahman

SloMo-Fast: Slow-Momentum and Fast-Adaptive Teachers for Source-Free Continual Test-Time Adaptation

arXiv (Cornell University), 2025

Preprint / Working PaperDOI

continual test-time adaptation
catastrophic forgetting
source-free adaptation
domain shift

Md Mubtasim Ahasan, Rafat Hasan Khan, Tasnim Mohiuddin, Aman Chadha, Tariq Iqbal, M Ashraful Amin, Amin Ahsan Ali, Md Mofijul Islam, AKM Mahbubur Rahman

FuseCodec: Semantic-Contextual Fusion and Supervision for Neural Codecs

arXiv (Cornell University), 2025

Preprint / Working PaperDOI URL

speech tokenization
cross-modal alignment
zero-shot speech synthesis
neural speech codec
temporal alignment
self-supervised speech models
speech transcription

Md Mubtasim Ahasan, Md Fahim, Tasnim Mohiuddin, AKM Rahman, Aman Chadha, Tariq Iqbal, M Ashraful Amin, Md Mofijul Islam, Amin Ahsan Ali

Dm-codec: Distilling multimodal representations for speech tokenization

arXiv preprint arXiv:2410.15017, pp. 25580-25602, 2024

Journal ArticleDOI URL

multimodal representation
speech tokenization
knowledge distillation

← All people