Temperament, defined as relatively stable, innate tendencies in emotional reactivity and self-regulation, is a robust correlate of childhood problem behaviors. However, while most studies focus on ...

Penn researchers have developed a smarter AI method for solving notoriously difficult inverse equations, which help scientists uncover hidden causes behind observable effects. By introducing ...

Penn Engineers have developed a new way to use AI to solve inverse partial differential equations (PDEs), a particularly challenging class of mathematical problems with broad implications for ...

Penn Engineers have developed a new way to use AI to solve inverse partial differential equations (PDEs), a particularly challenging class of mathematical problems with broad implications for ...

The flat source (FS) approximation assumes the source is uniform within a small region, while the linear source (LS) approximation allows it to vary linearly. Accurate modeling of neutron transport is ...

Abstract: We present a framework for fine-tuning flow-matching generative models to enforce physical constraints and solve inverse problems in scientific systems. Starting from a model trained on ...

Abstract: With the development of radar stealth technology, aircraft stealth design requires higher electromagnetic calculations. Electromagnetic calculation is the key link connecting theoretical ...

Abstract: We introduce a computationally efficient image reconstruction method that accelerates microwave tomographic imaging while maintaining the accuracy of traditional methods. The new method ...

This work introduces a model-agnostic framework for training and inference to enable accurate partial differential equation solving (down to double precision) for problems with arbitrary sizes and ...

摘要: The application of Eulerian codes for the numerical solution of the kinetic equations of plasmas has become a powerful numerical tool. In the present work, we use an Eulerian Vlasov code for the ...