Vaibhavi Lokegaonkar

I am Vaibhavi Lokegaonkar, a Master's student in Computer Science at the University of Maryland, College Park. I conduct research on audio generation under the guidance of Prof. Dinesh Manocha and Prof. Ramani Duraiswami at the GAMMA and PIRL labs.

Currently, my research focuses on conditioning methods for continuous-space audio generation. Over the past year, I have worked on detailed text and video conditioned music generation.

I also explore domains beyond audio generation. This summer, I worked at Capital One as an AI Engineering intern, where I focused on inference optimization using KV-cache management. Before UMD, I completed my undergraduate studies at IIIT Bangalore, where I worked on machine learning for healthcare, including video-based detection of self-stimulatory behaviours to support autism screening.

An interesting problem is all it takes to draw me in, whatever the domain. I am always open to new collaborations, so feel free to drop an email.