4 papers
METRO: Metric-Enhanced Token Routing Operator
Nodens Koren, Thomas Hofmann, Georgios Kissas
State-of-the-art neural operators scale to complex meshes via slice-and-process architectures, yet many rely on linear compatibility scores for latent tokenization. Under common fe…
Advectra: Asymmetric Latent Transport for Non-Stationary Physics
Nodens Koren, Thomas Hofmann, Georgios Kissas
Many latent neural operators represent input and output fields in a stationary latent chart. In particular, common latent routing mechanisms use fixed or shared assignment weights…
Emulating the complex galactic-scale orbital dynamics of LISA massive black hole pairs with normalizing flows
Pedro R. Capelo, Carlos Moreno Martinez, Nodens Koren +6
Massive black hole (MBH) pairs, formed in galaxy mergers, may coalesce in a burst of gravitational waves. Estimating the coalescence time-scales and rates is a long-standing astrop…
The Map Behind the Flow: Finite-Step Gradient Descent as a Dynamical System
Thomas Hofmann
Many phenomena of deep learning are dynamical: they concern not only which minima exist, but how gradient descent reaches, avoids, or selects among them. Edge-of-stability behavior…