Onkar's expertise spans continual learning, generative modeling, Natural Language Processing (NLP), and Computer Vision (CV), with a strong focus on multi-modal interactions. He is collaborating with the Machine and Hybrid Intelligence Lab at Northwestern University on cutting-edge projects, including synthetic data generation for CT/MRI images using Diffusion models and groundbreaking work in Video Diffusion. Onkar has also made significant contributions to signal processing, particularly in text-to-speech (TTS) and speech enhancement.He has published papers in top-tier journals and conferences such as the Journal of System Architecture, TPAMI, TACL, ECCV, ACL, EMNLP, ICASSP, and WACV. Driven by a passion for developing novel ideas and implementing them, Onkar is dedicated to advancing AI through continuous research and collaboration.