Fazli Imam

Hi, I’m an AI Researcher (Level II) at MBZUAI, supervised by Dr. Alham Fikri Aji at MBZUAI, focusing on exciting challenges in multimodality and visual temporal reasoning capabilities of vision-language models.

Previously, I earned my master’s degree in machine learning from MBZUAI where I was supervised by Dr. Hisham Cholakkal.

Before venturing into academic research, I honed my skills as a Data Scientist at Stax Inc.. and at NICST, where I applied data-driven insights to solve complex use cases.

I'm currently seeking Data Science and Machine Learning job opportunities. Feel free to reach out if you have any questions or would like to know more.

Email  /  Resume  /  Scholar  /  LinkedIn  /  Github

We propose a label-free prompt-tuning method that leverages the rich visual features of self-supervised learning models (DINO) and the broad textual knowledge of large language models (LLMs) to largely enhance CLIP-based image classification performance using unlabelled images.

We proposed TemporalVQA,a benchmark to evaluate the temporal reasoning capabilities of Multimodal Large Language Models (MLLMs) in tasks requiring visual temporal understanding.

We extend Statement Tuning to multilingual NLP tasks, investigating whether encoder models can achieve zero-shot cross-lingual generalization and serve as efficient alternatives to memory-intensive LLMs for low-resource languages

A Culturally-diverse multilingual Visual Question Answering benchmark, designed to cover a rich set of languages and cultures, where we engage native speakers and cultural experts in the data collection process.

We introduce a computer vision and machine learning-based system to automate the processing of minor automobile accident claims, incorporating damage assessment, repair cost estimation, and policyholder churn prediction to improve efficiency and retention outcomes.