I am a Ph.D. candidate at the University of Tennessee, Knoxville, focusing on large-scale representation learning for domain-specific agricultural applications. My work at UT Smart Agriculture Lab centers on self-supervised learning, computer vision, data engineering, and rigorous experimental evaluation, with an emphasis on building and benchmarking models that perform reliably in real-world agricultural environments.
Before my current research, my background was in robotics and autonomous systems, where I developed software for humanoid soccer robots competing in the RoboCup Humanoid League. Our team achieved 1st Place in 2015 (China) and 3rd Place in 2014 (Brazil), an experience that strengthened my skills in real-time perception, embedded programming, and vision-based decision making. This work directly led to my early open-source contributions, including HumanoidSoccerRobot and Pro-IMU.
I am also deeply interested in Natural Language Processing for low-resource languages, particularly Persian, and I am passionate about developing open-source tools and datasets that strengthen the Persian AI ecosystem. This interest led me to initiate projects such as Shekar, a Python toolkit for Persian NLP, and NeyShekar, a large-scale open Persian speech dataset, both designed to advance research, resource availability, and community-driven development for Persian language technologies.