I am Shifat Islam, a Research Engineer with expertise in NLP, Computer Vision, and Multimodal AI. My work focuses on domain-adapted LLMs and multimodal systems for healthcare, especially in low-resource and linguistically diverse settings. I’ve conducted research in clinical NLP, mental health informatics, and bias-aware AI, with a focus on SRMH, and have published in peer-reviewed journals and international conferences.
Research Interests
NLP specially LLM, Computer Vision in Medical & Agriculture, Vision-language models, AI in healthcare: Public health risk assessment (SRMH), Multimodal AI, Generative AI
Education
Master of Science in Computer Science and Engineering (M.Sc.Eng.) — Bangladesh University of Engineering and Technology (BUET), Dhaka, Bangladesh Supervisor: Dr. Rifat Shahriyar
Bachelor of Science in Computer Science and Engineering (B.Sc.) — Ahsanullah University of Science and Technology (AUST), Dhaka, Bangladesh Supervisor: Mr. Faisal Muhammad Shah
Skills
Proficient in programming, deep learning frameworks, data analysis, computer vision, and NLP tools commonly used in research and development:
Experience
Research Engineer — Institute of Research, Innovation, Incubation & Commercialization (IRIIC), United International University (UIU) Supervisor: Dr. Khondaker Abdullah-Al-Mamun
Research Assistant — Bangladesh University of Engineering and Technology (BUET) Supervisor: Dr. Rifat Shahriyar
Postgraduate Research — Applicability of AI in Public Health Risk Assessment (SRMH) for LMIC Supervisor: Dr. Rifat Shahriyar, BUET
Undergraduate Research — Visual Question Answering in Bengali: A Deep Learning Approach Supervisor: Mr. Faisal Muhammad Shah, AUST
Research
Journal Papers
Shifat Islam, Rifat Shahriyar, Abhishek Agarwala, Marzia Zaman, Shamim Ahamed, Rifat Rahman, Moinul H. Chowdhury, Farhana Sarker, Khondaker A. Mamun. “Artificial intelligence-based risk assessment tools for sexual, reproductive and mental health: a systematic review.” BMC Medical Informatics and Decision Making, Springer Nature, 2025. DOI
Bidyarthi Paul, Faika Fairuj Preotee, Shuvashis Sarker, Shamim Rahim Refat, Shifat Islam, Tashreef Muhammad, Mohammad Ashraful Hoque, Shahriar Manzoor. “ANCHOLIK-NER: A Benchmark Dataset for Bangla Regional Named Entity Recognition.” Under Review at PLOS ONE. arXiv
Conference Papers
Shifat Islam, Abhishek Agarwala, Emon Ghosh. “Code_Gen at BLP-2025 Task 1: Enhancing Bangla Hate Speech Detection with Transformers through Token-Aware Adversarial Contrastive Training and Layer-wise Learning Rate Decay.” IJCNLP-AACL BLP, 2025. DOI
Abhishek Agarwala, Shifat Islam, Emon Ghosh. “Code_Gen at BLP-2025 Task 2: BanglaCode: A Cross-lingual Benchmark for Code Generation with Translation and Assertion Strategies.” IJCNLP-AACL BLP, 2025. DOI
Shifat Islam, MD. Shorif Uddin, Rayhan Uddin Bhuiyan, Azizul Fayaz, Faika Fairuj Preotee, Mohammad Shahmidul Islam. “Comparative Study of LLMs and Transformers for Bangla Healthcare Paraphrasing.” ICCIT 2025
Shifat Islam and Mithila Arman. “Transformer-Based Extreme Selfie Detection for Enhancing Safety in Hazardous Environments.” IEEE WIECON-ECE, 2024. DOI
M. H. Rafi, Shifat Islam, S. M. Hasan Imtiaz Labib, S. S. Hasan, F. M. Shah and S. Ahmed. “A Deep Learning-Based Bengali Visual Question Answering System.” IEEE ICCIT, 2022. DOI
M. R. Hasan, N. Jahan, Shifat Islam and T. Muhammad. “Deep Learning-based Multi-Class Brain Abnormality Diagnosis on Bangladeshi MRI Images.” IEEE BECITHCON, 2024. DOI
S. Sarker, S. R. Refat, F. F. Preotee, Shifat Islam, T. Muhammad and M. A. Hoque. “An Exploratory Approach Towards Investigating and Explaining Vision Transformer and Transfer Learning for Brain Disease Detection.” IEEE ICCIT, 2024. DOI
M. A. Alam Khandaker, Z. S. Raha, Shifat Islam and T. Muhammad. “Explainable AI-Enhanced Deep Learning for Pumpkin Leaf Disease Detection: A Comparative Analysis of CNN Architectures.” IEEE ICCIT, 2024. DOI
F. F. Preotee, S. Sarker, S. R. Refat, T. Muhammad and Shifat Islam. “An Approach Towards Identifying Bangladeshi Leaf Diseases through Transfer Learning and XAI.” IEEE ICCIT, 2024. DOI
Under Review
Shifat Islam, Shuvashis Sarker, Bidyarthi Paul, Mahbub Hasan and Mohammad Shohel Rana. “VGDNet: An Attention-Based Weighted Fusion Architecture for Automated Tomato Leaf Disease Detection with Explainable AI.” Qpain 2025
Datasets
BengaliVQA: A Benchmark Dataset for Bengali Visual Question Answering — Mendeley Data, 2025. Contributors: Shifat Islam, SM Sajid Hasan, Mahamudul Hasan Rafi, S.M. Hasan Imtiaz Labib, Faisal Muhammad Shah. DOI:10.17632/Y9FW6K37N9.1
ANCHOLIK-NER: A Benchmark Dataset for Bangla Regional Named Entity Recognition — Mendeley Data, 2025. Contributors: Bidyarthi Paul, Faika Fairuj Preotee, Shuvashis Sarker, Shamim Rahim Refat, Shifat Islam, Tashreef Muhammad, Mohammad Ashraful Hoque, Shahriar Manzoor. DOI:10.17632/gbkszkt8z3
PerilPix: A Curated Dataset for Detecting Extreme and Normal Selfies — Mendeley Data, 2025. Contributors:Shifat Islam, Mithila Arman. DOI:10.17632/3RWJGBJ4K8.1
Projects
Susastho.AI Chatbot for Adolescents — Conversational AI chatbot for adolescent SRMH awareness. Framework: Flask, PyTorch, LangChain.
Intent-Based Search Engine (2025) — Semantic product search using FAISS for intent-based retrieval. Framework: PyTorch, LangChain, LangGraph, FAISS, Redis, Docker.
BLP25 Task 1: Bangla Multi-task Hate Speech Identification (2025) — Multi-label classifier across subtasks. Framework: PyTorch, Transformers. GitHub
BLP25 Task 2: Code Generation in Bangla (2025) — Code generation from Bengali instructions. Framework: PyTorch, Unsloth, OpenAI SDK. GitHub
Grants and Achievements
Best Shared Task Paper Award, BLP Workshop @ IJCNLP-AACL 2025 — Certificate
Awarded the SEU IRT Research Grant (2025) for contributing to REG-NER Info Page
Institute for Advanced Research (IAR) Publication Grant of United International University
