Welcome to our lab: AXIOM
Accelerator for eXplainable Intelligence through Optimization and Machine Learning
What We Do
We design coding-theoretic methods that make large-scale matrix and learning computations faster and more resilient to slow workers. Our work focuses on efficiency and scalability of distributed computing systems.
We study the reliability, safety and trustworthiness of large language models across real-world decision-making settings. We focus on detecing and mitigating vulnerabilities including hallucination or misalignment.
We develop distributed and federated machine learning algorithms that enable intelligent systems to learn from decentralized data while addressing communication, privacy, robustness, and heterogeneity challenges.
We apply machine learning methods to impactful domains including healthcare, power systems, communication networks, agriculture and engineering systems to advance practical tools across interdisciplinary applications.
Members
Arijit Ghosh
Arijit is a PhD student in Electrical and Computer Engineering at the University of Akron. He got his Master's from Cleveland State University. He has nearly a decade experience in machine learning and generative AI. His research interests include improving the performance of open source LLMs in terms of decision making and trustworthiness.
Sourav Dey
Sourav is currently a Ph.D. student in Electrical and Computer Engineering at the University of Akron. He did BSc in Electrical and Electronic Engineering from Chittagong University of Engineering and Technology (CUET). His research interests include deep learning, biomedical signal processing, distributed learning and large language model applications.
Nafisa Islam
Nafisa is currently pursuing her Ph.D. in Electrical and Computer Engineering at the University of Akron. She earned her undergraduate degree in Electronics and Telecommunication Engineering from Chittagong University of Engineering and Technology (CUET). Her research interests include distributed computing, computer vision, and machine learning.