DataGen Lab

Established in 2021, the Data Generation Lab (DataGen) is a premier research facility dedicated to the advancement of Generative Artificial Intelligence (AI). Under the directorship of Dr. Aamir Wali, the lab focuses on producing synthetic digital data—images, audio, video, text, and time-series—by modeling the underlying data distributions using state-of-the-art machine learning and AI tools. The lab emphasizes not just realistic content generation but also meaningful applications in healthcare, education, accessibility, and communication technologies.

Our vision is to explore and develop innovative AI solutions by understanding how different forms of data behave and can be generated to enhance real-world applications. DataGen pioneers methods like GANs, Transformers, and Cellular Automata-based synthesis to generate high-quality data for cutting-edge AI systems. The lab’s core research areas include: Speech Synthesis, Image Synthesis & Medical Imaging, Video Generation (Sign Language), Text Generation & Summarization and Data Augmentation for Machine Learning Models.