My primary research focus lies at the intersection of human visual cognition and deep learning as I am interested in how our decades of understanding the human visual system can inform and enhance modern computer vision models. I am particularly interested in leveraging psychovisual processing principles to develop more efficient and robust machine learning architectures. While large-scale models have shown impressive results, I believe that drawing inspiration from human visual processing will be crucial for developing resource-efficient solutions that can operate effectively with limited computational resources. What sets my journey apart is the uncommon path I chose: simultaneously pursuing my PhD at Penn State while maintaining a full-time professional career. This exceptional dual commitment not only demonstrates my passion for the field and organizational capabilities but also provided me with a unique advantage. Unlike the traditional path of transitioning directly from undergraduate studies to doctoral research, my concurrent industry experience has enabled me to bridge the gap between theoretical foundations and practical applications. This distinctive perspective continues to influence my approach to computer vision research, allowing me to identify and pursue solutions that are both academically rigorous and practically viable. |