Music. Co-Creative. AI
We meet weekly to read a paper or two at the intersection of music and ML. After each session, we write up notes, post the slides, and sometimes record video or build a small demo. Most of what we make ends up on this site.
Reading Schedule
What we're currently reading
Interactive Notes
Notes from past sessions
Audio Representations
Contrastive language-audio alignment (CLAP) and self-supervised music understanding (MERT)
Two complementary approaches to learning what music 'means' to a neural network: CLAP aligns audio with natural-language descriptions through contrastive learning, while MERT learns musical structure from audio alone via masked acoustic modeling with dual teachers.
LLMs for Audio Effects
Two papers from the Sony AI / KAIST group on using language models to drive EQ, compression, and reverb: first by predicting parameters, then by calling tools
Why audio effects are a uniquely tractable target for LLMs, and how the Doh et al. team moves from parameter regression (LLM2Fx) to tool-calling chains with chain-of-thought planning (LLM2Fx-Tools).
What we read
ML papers about music: synthesis, transcription, generative models, anything with a loss function and an audio output. We work through one or two a week.
How we share
Each session gets interactive notes with visualizations and audio demos (and usually some PyTorch). The goal is real intuition, not just a summary of the abstract.
Who it's for
Researchers, engineers, musicians, students. Anyone who wants to actually dig into the papers rather than just hear about them. Show up, ask questions, bring coffee.
Want in, have a paper to suggest, or want to present one?
Join the Google Group