Prince Mireku
Research Assistant @ CKT UTAS
mirekuprince23@gmail.com
I am currently a research assistant at
C.K.T UTAS, working under the guidance of
Prof. Mohammed I. Daabo.
We explore efficient ways to synergistically combine foundational Computer Vision and Natural Language Processing
models, targeting core recipes to offer novel approaches for training, evaluation, and inference in resource-constrained settings.
In parallel, I am mentored by Mr. Strato Bayitaa,
Mr. Strato Bayitaa
,
a Google PhD Scholar at Oregon State University. Our research focuses on multimodal learning approaches and their applications in healthcare.
Specifically, we experiment with vision and language alignment techniques to address challenges in the vision-language space.
The ultimate goal is to develop reliable and interpretable models for robust medical tasks.
My broader research interests include:
Jul 2024 | I'll be presenting our work on Multimodal Multilingual African Dataset at ML Collective's 22nd Research Jam. |
Jul 2024 | Joined SMART Lab @ NDSU as a Research Intern. |
Jun 2024 | Joined @Black in AI Community. |
Apr 2024 | Reviewing applications for Deep Learning Indaba 2024. |
Feb 2023 | Started RA @ C.K.T University of Technology and Applied Sciences. |
The scope of Ghanaian Language; Twi datasets is insufficiently diverse, hindering a multitude of applications. To address this, we are curating a comprehensive corpus from literature, media, and synthetic data, covering formal, informal, and conversational registers. Using advanced data collection methods and rigorous validation, including transformer-based models and expert human verification, we ensure a high-quality data repository for robust NLP applications.
An ensemble approach to enhance efficiency and interpretability in Biomedical AI through majority voting. This project focuses on equipping large language models (LLMs) with multimodal capabilities through feature alignment using a vision encoder. Additionally, we are experimenting with synergistically combining language (LLM) and vision (ViTs) models to to enhance interpretability in medical diagnosis.
OngoingThis research project focuses on enhancing the reliability of Residue Number System (RNS) arithmetic operations through the development of effective fault tolerance techniques. We also proposed a novel integrated fault-tolerant technique that combines redundant residues, modular checksums, and Reed-Solomon codes for error detection & correction. This integrated approach aims to improve fault coverage and reliability in RNS arithmetic operations compared to existing solutions, with manageable overhead.
B.Sc. Computer Science