Theoretical Physic
Theoretical physics is currently undergoing a transformation driven by the integration of machine learning techniques. Research focuses on developing and applying novel neural network architectures, such as physics-informed neural networks (PINNs) and variants of Kolmogorov-Arnold networks, to solve complex differential equations and model physical phenomena across diverse fields, from fluid dynamics and quantum physics to material science and robotics. This interdisciplinary approach promises to accelerate scientific discovery by enabling more efficient simulations, improved data analysis, and the potential discovery of new physical laws through the analysis of statistical patterns in existing equations.
Papers
Control of Overfitting with Physics
Sergei V. Kozyrev, Ilya A Lopatin, Alexander N Pechen
A recent evaluation on the performance of LLMs on radiation oncology physics using questions of randomly shuffled options
Peilong Wang, Jason Holmes, Zhengliang Liu, Dequan Chen, Tianming Liu, Jiajian Shen, Wei Liu
On the physics of nested Markov models: a generalized probabilistic theory perspective
Xingjian Zhang, Yuhao Wang
Harnessing Scale and Physics: A Multi-Graph Neural Operator Framework for PDEs on Arbitrary Geometries
Zhihao Li, Haoze Song, Di Xiao, Zhilu Lai, Wei Wang
Physics Encoded Blocks in Residual Neural Network Architectures for Digital Twin Models
Muhammad Saad Zia, Ashiq Anjum, Lu Liu, Anthony Conway, Anasol Pena Rios
Physics meets Topology: Physics-informed topological neural networks for learning rigid body dynamics
Amaury Wei, Olga Fink