Litcius/Paper detail

Universal Physics Transformers: A Framework For Efficiently Scaling Neural Operators

Benedikt Alkin, J. Brandstetter, Andreas Fürst, Lukas Gruber, Markus Holzleitner, Simon Schmid

202413 citationsDOI

Topics & Concepts

ScalingComputer scienceArtificial neural networkAlgorithmMathematicsPhysicsOperator (biology)Artificial intelligenceRepresentation (politics)Theoretical computer scienceStatistical physicsAlgebra over a fieldKey (lock)Feature (linguistics)Context (archaeology)Theoretical physicsNoise (video)Neural Networks and Reservoir ComputingModel Reduction and Neural NetworksNeural Networks and Applications
Universal Physics Transformers: A Framework For Efficiently Scaling Neural Operators | Litcius