Physical Fields
PulseAugur coverage of Physical Fields — every cluster mentioning Physical Fields across labs, papers, and developer communities, ranked by signal.
-
Neural Fields' Adaptation Geometry Offers New Insights Beyond Reconstruction
Researchers have developed a new method to analyze neural fields by examining their "adaptation geometry," which describes how easily a network can adjust to new data and what information it retains from past observatio…
-
JEPA-Anything framework enables domain-agnostic world modeling
Researchers have introduced JEPA-Anything, a new framework designed for domain-agnostic world modeling. This approach extends joint-embedding predictive architectures by employing orthogonal predictive factorization (OP…
-
New framework models constrained multi-output physical fields using row-wise PCA and GP
Researchers have developed a novel framework for simultaneously predicting multiple high-dimensional physical fields that are subject to linear equality constraints. This problem is common in physics and machine learnin…