Later today (3.45pm) Iβll be talking at the NSIA (network-science-ai.github.ioβ¦) workshop of @NetSciConf about (exciting!) work on the interplay between generalization and working memory limits. Come through!
Day 1 afternoon keynote talk given by Max Welling @wellingmax#ICLR2026
From Physics to AI to Materials; A Journey from Foundations to Impact
"Do we reward strange new, potentially paradigm-shifting ideas or do we focus on engineering, scaling and bold numbers?"
Looking forward to giving a keynote at the @icmlconf workshop on foundations of deep generative models. The submission deadline for papers is April 30th. Consider submitting - will be a very fun workshop!
We invite submissions to the ICML 2026 Workshop Foundations of Deep Generative Models: Understanding Memorization, Generalization, and Reasoning.
Submission deadline: April 30
Workshop website:
fdgm-workshop.github.io/FDGMβ¦
Today I will join the Future Humans team @berggruenInst for a conversation on diverse intelligences structured around their Future Wunderkammer futurerelics.berggruen.org
1/ New preprint!
When you coarse-grain a network, does the dynamics survive?
We prove exactly which coarse-grainings preserve random-walk dynamics across scales β and use it to compare renormalization methods.
w/ Francesco Guadagnuolo, @MarcoNurisso , Federica Galluzzi, @all_are