SCRAPL: Scattering Transform with Random Paths for Machine Learning
I’m excited to share our #ICLR2026 paper on SCRAPL: an algorithm that makes wavelet scattering transforms usable as differentiable loss functions!
paper: https://t.co/D0X4v80P9J
web: https://t.co/l6hc0zos5e
Say hello to Project LYDIA Phase II!
Developed in partnership with our friends at Roland Future Design Lab @RolandGlobal, we're proud to announce the next step in our journey towards neural hardware.
Article: https://t.co/kmKsghZ3Ld
Friends! We are attending #Superbooth 2026 in Berlin, May 7th-9th.
Join us at the @MyRoland booth for some hands-on time with Project LYDIA and a special preview of our upcoming product.👀
I’m at ICLR in Rio 🇧🇷 this week presenting SCRAPL today 15:15 - 17:45 at poster session 2, pavilion 3, #515. Come find me to chat about audio, wavelets, and optimization. 🌊 I’m always happy to grab a coffee so feel free to DM / email too!
SCRAPL: Scattering Transform with Random Paths for Machine Learning
I’m excited to share our #ICLR2026 paper on SCRAPL: an algorithm that makes wavelet scattering transforms usable as differentiable loss functions!
paper: https://t.co/D0X4v80P9J
web: https://t.co/l6hc0zos5e
Lastly, a huge thank you to my collaborators Vincent Lostanlen (@lostanlen), Emmanouil Benetos (@emmanouilb), and Mathieu Lagrange (@lagrangResearch), without whom this project would not have been possible! 9/9
SCRAPL: Scattering Transform with Random Paths for Machine Learning
I’m excited to share our #ICLR2026 paper on SCRAPL: an algorithm that makes wavelet scattering transforms usable as differentiable loss functions!
paper: https://t.co/D0X4v80P9J
web: https://t.co/l6hc0zos5e
SCRAPL for the JTFS in PyTorch is available now as a Python package (`pip install scrapl-loss`) and we provide open source code, experiments, and listening samples: https://t.co/H9aPpbiPpi 8/9
New VST3/AU plugin drop to kick off the week! 🚀
Stable Audio Open Small by @StabilityAI
Demucs stem separation
LoopGAN for generating audio loops
Many more models to come
All running locally on-device!
Opensource SDK and free plugin, enjoy!
https://t.co/ndSnXbcA96
Check out the paper, plugins, and code for more details, and join the Discord server to stay up to date. Finally, a huge thank you to my collaborators at Neutone for the amazing work they’re doing!
Neutone SDK: An Open Source Framework for Neural Audio Processing
We’ve finally published a paper for the Neutone SDK which I presented at AES AIMLA 2025 a few weeks ago!
arXiv: https://t.co/Vj4opVDyr4
code: https://t.co/L5E3J5Cb9g
discord: https://t.co/s2OfqjyxCh
@neutone_ai
At a time when many AI companies are competing with artists and training on their work without permission, the SDK democratizes this technology and provides a foundation for AI tools that enhance rather than replace human creativity.
https://t.co/aClnV72fY0
(8/8)