I am a 1st-year PhD candidate at Rutgers, advised by Dr. Sharon Levy. My research focuses on alignment and reasoning within multimodal and multilingual large language models (LLMs). My interest lies in knowledge representation and commonsense reasoning, especially within multilingual and multimodal contexts (encompassing vision, language, and acoustics). I am deeply invested in pushing the boundaries of natural language understanding and generation, focusing on creating models that are not only advanced but also fair, robust, and explainable. My passion also extends to the fusion of Computer Vision, HCI, and NLP to transcend traditional interfaces, enhance societal communication, and deepen our understanding of cognitive processes. 

Before joining Rutgers, I worked as a Senior Assessment Developer at Workera. I earned my bachelor’s in Computer Science and Engineering from the Chittagong University of Engineering and Technology (CUET), Bangladesh. I am extremely fortunate to be advised by Dr. Mohammed Moshiul Hoque. I am a recipient of the Fatima Al-Fihri Predoctoral Fellowship, where I am collaborated with UC Santa Barbara NLP Group on evaluating faithfulness in text-to-image model metrics. I am a former Undergraduate Research Student at CUET NLP lab, where I had the chance to work on developing benchmark corpus and frameworks for Bangla Natural Language Processing. I am a professional member of IEEE and the former Vice Chairman of IEEE CUET Women In Engineering Affinity Group.