Louis Bradshaw
CV
/ GitHub
/ Twitter
moc [tod] kooltuo [ta] 91auol
Hi! I'm a CS/ML PhD student specialising in Deep Learning. Prior to my PhD I studied Mathematics, focusing on Algebra and Geometry. My research interests are varied, they include:
- Generative Music: I'm interested in deep learning based generative models which are expressive, useful, and artistically interesting. My research has involved training and aligning musical transformer models for this purpose (see the Aria project).
- Multimodal ML: I'm investigating methods for integrating text and symbolic music (MIDI) with generative audio models. More generally, I'm interested in ways to improve multimodal foundation models.
- Natural Language Processing: I spend a lot of time applying techniques originally developed in NLP, to generative music. As such I spend a lot of time engaging with NLP research, primarily focusing on alignment and RLHF.
- Datasets and Evaluations: In an effort to accelerate research in generative music, I'm interested in building large open source music datasets. I research techniques for converting audio into symbolic data (e.g. AMT), as well as how to combine techniques from each domain.
Aria Project
I currently run a research project on building, scaling, and aligning transformer models for symbolic music. The project gets its codename, Aria, from the Goldberg Variations, and has attracted generous funding and compute support from both EleutherAI & StabilityAI. Other than building a powerful foundation model and personal artistic projects, my secondary aim is to build a generative compositional tool which is interesting and useful to both novices and experts alike. Although this project is still a work in progress and hasn't been publicly released, here are some early samples showcasing what it can do.
If you are interested finding out more about the Aria project, the best place is on the EleutherAI discord channel.
Misc
These essays [1, 2] and these books [3, 4, 5] had a big influence on me.