Onkar Susladkar
I am Onkar Kishor Susladkar, a PhD student at UIUC, focusing on multi-modal AI with a strong interest in video and image generation. My research centers on developing unified generative models that jointly process and generate video, speech, and language, enabling context-aware, temporally coherent, and causally consistent multi-modal systems. I have also worked extensively in speech and signal processing, including text-to-speech (TTS) and speech enhancement, with my work published in top-tier venues such as ICLR, CVPR TMI, TPAMI, ECCV, ACL, EMNLP, ICASSP, and WACV.