Louis Bradshaw
Curriculum Vitae
/ Google Scholar
/ GitHub
/ Twitter
l.b.bradshaw [at] qmul.ac.uk
I'm a CS/ML PhD student at C4DM, where I specialize in Deep Learning for Audio. Prior to my PhD, I studied Mathematics (Algebraic Geometry) at Imperial College London (BSc, MSc). My current research interests are varied and include:
Deep Learning for Music. I've led research projects in several core areas of generative music and information retrieval including: musical foundation models (see the Aria project), self-supervised representation learning, audio transcription (see Aria-AMT), and datasets (see Aria-MIDI). My research has broadly focused on improving symbolic models for modelling piano performance, and with the aim of creating real-time interactive systems human-AI co-creation.
Hybrid Audio/Language Models. I've developed a growing research interest in models that integrate audio with text or other token-based symbolic information. This includes areas such as neural audio codecs, automatic speech recognition, and audio-language models. I'm particularly interested in improving conversational speech foundation models (e.g., Moshi) through both architectural and data-centric approaches.
I'm also extremely interested in the engineering problems surrounding ML/DL. In my non-research time, I currently dedicate a portion to studying C++/CUDA. Outside of research, I have a deep love for mathematics, music production, and reading. The best part of doing a PhD is getting to learn from all kinds of people. If you are interested in collaborating, or just chatting about research, feel free to reach out!
News
- [Sep 2025] I'll be presenting our work on real-time, interactive generative music systems with our demo: The Ghost in the Keys at NeurIPS 2025, as well as at the AI4Music workshop.
- [Jun 2025] Our paper Scaling Self-Supervised Representation Learning for Symbolic Piano Performance was accepted to ISMIR 2025.
- [Jan 2025] Our paper Aria-MIDI: A Dataset of Piano MIDI Files was accepted to ICLR 2025.
- [Jan 2024] Thanks to StabilityAI and EleutherAI, who have provided us with significant compute sponsorship (10k A100 hours) for the Aria project.
Aria Project
The Aria project was a project to scale transformer-based foundation models for symbolic music. The project got its codename, Aria, from the Goldberg Variations, and has attracted generous compute support from EleutherAI & StabilityAI. The code and publications for our model can be found on the official repository.
If you are interested in 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.