M. Faizan Ali Khan

Cusack Lab

Trinity Institue for Neuroscience, Trinity College Dublin

Dublin, Ireland

I am a PhD candidate in Psychology at Trinity College Dublin, working in the Cusack Lab under the supervision of Prof. Rhodri Cusack. My research aims to develop physics-informed neural network frameworks that integrate domain knowledge of MRI acquisition with data-driven learning. Specifically, I investigate methods for multiband fMRI reconstruction, particularly in infant imaging, where motion presents a significant challenge, and I aim to jointly estimate and correct motion directly in k-space, where the raw signal contains richer and less-processed information compared to the image domain.

Before beginning my PhD, I completed my Master’s in Robotics and Intelligent Machine Engineering at the National University of Sciences and Technology (NUST), Islamabad, Pakistan. My Master’s research focused on developing a hybrid deep neural network architecture for brain tumor segmentation using multi-modal structural brain MRI. This work was supervised by Dr. Sara Baber Sial.

news

Sep 08, 2025	I am delighted to share that I have joined the Cusack Lab as a PhD student, where I will be working on research at the intersection of neuroimaging, machine learning, and motion correction.
Apr 24, 2025	I am delighted to share that our paper, “RAG-Powered LLMs for QA: Evolution, Challenges, Applications, and Future Directions,” received the Best Paper Award in the Software Engineering Track at the 5th International Conference on Communication Technologies (ComTech), held at the Military College of Signals, Rawalpindi.
Feb 22, 2025	I am delighted to share that I have completed my Master’s degree in Robotics and Intelligent Machine Engineering at the National University of Sciences and Technology, Islamabad, Pakistan.

recent blog posts

Oct 13, 2024	The Next Frontier in Computer Vision: Are CNNs Ready to Take the Lead?

selected publications

RAG Powered LLMs for QA: Evolution, Challenges, Applications, and Future Directions

Hafiz Muhammad Ali Zeeshan, Muhammad Faizan, Usman Zia, and 1 more author

In 2025 International Conference on Communication Technologies (ComTech), 2025

Abs Bib HTML

Large language models (LLMs) are evolving to excel in challenging tasks such as text generation, mathematical reasoning, code generation, question answering, text summarization, etc. However, the responses generated by LLMs are prone to hallucinations, out-of-the-date knowledge, and non-transparent and untraceable reasoning. Retrieval augmented generation (RAG) addresses these shortcomings by incorporating external knowledge in the LLM prompt. RAG combines parametric knowledge of LLM with non-parametric knowledge from external databases by efficient retrieval techniques. This comprehensive review paper provides a detailed overview of the significance and emergence of RAG. Moreover, the building blocks of RAG are thoroughly discussed along with the evolution, challenges, and current research trends of deploying RAG-based applications. Finally, we explore the RAG performance enhancement strategies while also underlining the potential future research directions.
@inproceedings{zeeshan2025rag, title = {{RAG Powered LLMs for QA: Evolution, Challenges, Applications, and Future Directions}}, author = {Zeeshan, Hafiz Muhammad Ali and Faizan, Muhammad and Zia, Usman and Gohar, Abdullah}, booktitle = {2025 International Conference on Communication Technologies (ComTech)}, pages = {1--6}, year = {2025}, organization = {IEEE}, }