Machine LearningFeatured briefing
First-hand information for everyone
Researchers introduce a new kind of graph neural network that builds local gauge symmetry into its core. The network works with matrix-value
The paper introduces a new kind of graph neural network that builds local gauge symmetry into its core. The authors embed non-Abelian gauge
Researchers introduce MathNet, a large collection of competition-level math problems and a set of tests designed to push how well AI can bot
This paper explains when and why a broad class of iterative algorithms behaves the same on many large matrices, including some deterministic
Large vision-language models can name objects that are not actually in an image. This paper studies that problem, which is called object hal
Scientists present a new method that uses neural-network flows to sample equilibrium states of condensed matter while respecting the periodi
This paper studies a common problem: finding the minimum of a smooth, strongly convex loss when we only see noisy samples. The authors show
Researchers propose a simple change to how diffusion models draw samples that can cut the computing needed to generate images. The new Multi
This paper presents ThinkJEPA, a method that combines two ways of understanding video to predict future states for tasks like hand-manipulat
This paper is a wide-ranging survey of how artificial intelligence (AI) methods are being applied to materials plasticity — the permanent sh