I am a master’s student in Computer Science at the University of Toronto co-supervised by Prof. Tovi Grossman of DGP and Prof. Sageev Oore of the Vector Institute. I am currently applying to Ph.D. positions where I can continue to create new systems that enhance our abilities to create music. More specifically, I want to focus on enabling live interactions with powerful generative models in a way that is cohesive with traditional senses of music making like improvisation or performance.
During my master’s, I focused on designing experimental applications that augmented human creativity with AI. I just completed a project, SynthScribe, which facilitates the use of synthesizers by letting musicians use text and audio as an intuitive control modality. We acheive this by building several features that use latent representations of text and audio from the deep learning model LAION-CLAP. Our features allow musicians to search for and modify synthesizer sounds while also allowing musicians to create completely new sounds. This has recently been accepted at the ACM conference on Intelligent User Interfaces (IUI) and was previously featured in the NeurIPS workshop for Creativity and Design. In the first half of my master’s, I focused on designing a novel interactive system, Promptify, that used chat optimized large language models to facilitate the use of text-to-image models. I had the pleasure of presenting this work at UIST 2023.
I recieved my bachelor’s degree in Engineering Science from the University of Toronto where I majored in Machine Intelligence. I also completed a professional experience year working at AMD as a Machine Learning engineer where I developed in-house applications to aid with the detection of regressive code.