Author

Scott H. Hawley

h-index 2 View on Semantic Scholar

We have 2 of 5 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Aug 2026

Helping Music Co-Creation Agents'Listen'Well: Hierarchical Self-Supervised World Models for Understanding and Generation

A hierarchical self-supervised ``world model'' for symbolic music is presented, using a 2.55M-parameter Swin V2 encoder trained on MIDI piano-roll images with JEPA-style objectives (pitch- and time-shift equivariance, masked embedding prediction, and a distributional regularizer), using no labels and no music-theory vo...

Scott H. Hawley · 0 citations

Jul 2026

MIDI-RAE-JEPA: Hierarchical Representation Learning and Generation for Symbolic Music

The results suggest that equivariance-based SSL objectives, combined with sufficient fine-level encoder capacity, provide a viable path toward semantically rich, generatively useful representations of symbolic music.

Scott H. Hawley · arXiv.org · 1 citation