Hi,
I am a PhD student in Computer Science at the University of Kentucky, advised by Dr. Abdullah-Al-Zubaer Imran. My research focuses on computer vision, multimodal models, medical imaging, generative models, and fairness in AI. Previously, I worked as a Machine Learning Engineer at TigerIT Bangladesh Ltd.. I earned both my master’s and undergraduate degrees from the Department of Computer Science and Engineering, University of Dhaka, Bangladesh.
Research Interests:
- Multimodal Data Analysis
- Vision Language Models
- Generative Models
- Medical Imaging
- Computer Vision for Healthcare
🔥 News
- 2025.09: Presenting poster at the CLIMBS Super Collider Event 2025!
- 2025.09: Presenting at the MIDL Young Researcher Showcase!
- 2025.07: Passed my PhD Qualifying Examination!
- 2025.05: Joined the Association of Data and Computation (ADC) as Treasurer!
- 2025.04: Short Paper accepted at CVPR workshop MMFM 2025!
- 2025.04: Paper accepted at EMBC 2025!
- 2025.04: Presenting paper at ISBI 2025 in Houston, TX!
- 2025.04: Presenting at CCTS Spring Conference 2025 in Lexington, KY!
- 2025.03: Giving a talk at the KCS Seminar Spring 2025!
- 2025.01: Paper accepted at ISBI 2025!
- 2024.10: Presented my paper at MICCAI ADSMI 2024 in Marrakesh, Morocco.
📝 Publications
-
Differential Attention for Multimodal Crisis Event Analysis
Nusrat Munia, Abdullah-Al-Zubaer Imran
CVPRw MMFM3: The 3rd Workshop on What is Next in Multimodal Foundation Models? 2025.
Paper Code -
Class-N-Diff: Classification-Induced Diffusion Model Can Make Fair Skin Cancer Diagnosis
Nusrat Munia, Abdullah-Al-Zubaer Imran
47th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) 2025.
Paper | Code -
Prompting Medical Vision-Language Models to Mitigate Diagnosis Bias by Generating Realistic Dermoscopic Images
Nusrat Munia, Abdullah-Al-Zubaer Imran
International Symposium on Biomedical Imaging (ISBI) 2025.
Paper | Code -
Evaluating Deep Learning Models for Breast Cancer Classification: A Comparative Study
Sania Eskandari, Ali Eslamian, Nusrat Munia, Amjad Alqarni, Qiang Cheng
Medical Imaging 2025: Digital and Computational Pathology, 2025.
Paper -
DermDiff: Generative Diffusion Model for Mitigating Racial Biases in Dermatology Diagnosis
Nusrat Munia, Abdullah-Al-Zubaer Imran
MICCAI Workshop on Advancing Data Solutions in Medical Imaging AI 2024 [Top 13%].
Paper | Code
🎤 Presentations
- [Oral] YR Showcase Event 2025, Online - Generative Diffusion Models for Fair Dermatology AI Event
- [Poster] CLIMBS SuperCollider 2025, Lexington, KY - Enhancing Multimodal Reasoning for Crisis Event Analysis with Vision Language Models and Attention Modules [PDF]
- [Poster] EMBC 2025, Copenhagen, Denmark - Class-N-Diff: Classification-Induced Diffusion Model Can Make Fair Skin Cancer Diagnosis [PDF]
- [Poster] CVPRw 2025, Nashville, TN - Differential Attention for Multimodal Crisis Event Analysis [PDF]
- [Oral] ISBI 2025, Houston, TX - Prompting Medical Vision-Language Models to Mitigate Diagnosis Bias
- [Oral] CCTS 2025, Lexington, KY - Prompting Medical Vision-Language Models to Mitigate Diagnosis Bias
- [Oral] KCS Seminar - Spring 2025, Lexington, KY - Generative Dermatology AI for Diagnostic Bias Mitigation [Video]
- [Oral & Poster] MICCAI ADSMI 2024, Marrakesh, Morocco - DermDiff: Generative Diffusion Model for Mitigating Biases [PDF]
📖 Education
- PhD in Computer Science, University of Kentucky (2023–Present)
- M.S. in Computer Science and Engineering, University of Dhaka (2020–2023)
- B.S. in Computer Science and Engineering, University of Dhaka (2016–2019)
💼 Experience
🔬 Research Experience
Graduate Research Assistant | University of Kentucky | Aug 2023 – Present
Multimodal Crisis Event Analysis
- Developing multimodal AI models for crisis detection and damage assessment using vision-language models
- Integrating fairness evaluation mechanisms for vulnerable communities across Kentucky counties
Generative Dermatology AI
- Developed diffusion transformer models to mitigate racial biases in skin disease classification
- Created generative models to address data imbalance for underrepresented demographic groups
Graduate Student Researcher | University of Dhaka | Mar 2020 – Feb 2023
Text Summarization Research
- Developed extractive text summarization models using BERT for entity-based content selection
- Created abstractive summarization systems using LSTM encoder-decoder architectures
🏢 Industry Experience
Software Engineer - Machine Learning | TigerIT Bangladesh Ltd. | Jun 2021 – Jul 2023
Neural Machine Translation
- Trained and developed bidirectional English-Bangla translation systems
- Implemented transformer-based architectures for improved translation quality
Language Processing Systems
- Developed Banglish (Bangla written in English script) detection models
- Built transliteration systems converting Banglish text to native Bangla script
- Created manually annotated datasets for model training
Backend Development
- Maintained web servers for Commchat messaging application
- Implemented new features and resolved system bugs
🎓 Teaching Experience
Graduate Teaching Assistant | University of Kentucky | Fall 2024
CS-216: Introduction to Software Engineering Techniques
- Led laboratory sessions and provided hands-on coding instruction
- Conducted office hours and assisted students with programming assignments
- Graded lab assignments and examinations
🏆 Awards and Fellowships
- 2025: Graduate Student Block Funding, University of Kentucky (Travel Grant for ISBI 2025)
- 2021: Fellowship by ICT Division, Bangladesh
- 2019: Champion - Bracathon 3.0, Bangladesh
📜 Affiliations
- Treasurer, Association for Data and Computation, CS, UKy
- MICCAI Student Member
- IEEE Student Member
- IEEE EMBS Member