Author

B. Hayes

2 papers indexed here

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 Sep 2026

Off-manifold robustness in synthesizer inversion with joint distribution flow matching

Recent work on synthesizer inversion shows that generative models outperform deterministic approaches by explicitly modeling the ambiguity in mapping audio to parameters. Training such models, however, requires audio-parameter pairs, which are typically obtained by rendering sampled or preset parameters through the syn...

B. Hayes · 0 citations

#machine learning Preprint Sep 2026

Synth-JEPA: Joint Embedding Prediction for Renderer-Free Synthesizer Parameter Search

The introduction of Synth-JEPA, which learns mutually predictive audio and parameter representations from paired synthesizer data, and its matching quality continues to improve with additional test-time search, allowing compute to be traded for match quality.

B. Hayes, Hao-Kun Tian, Stefan Lattner · 0 citations