4 papers
Accurate and scalable deep Maxwell solvers using multilevel iterative methods
Chenkai Mao, Jonathan A. Fan
Neural networks have promise as surrogate partial differential equation (PDE) solvers, but it remains a challenge to use these concepts to solve problems with high accuracy and sca…
Near-field optical mode engineering-enabled freeform nonlocal metasurfaces
Zhongjun Jiang, Tianxiang Dai, Shuwei Guo +6
Nanophotonic technologies inherently rely on tailoring light-matter interactions through the excitation and interference of deeply confined optical resonances. However, existing co…
Shaping freeform nanophotonic devices with geometric neural parameterization
Tianxiang Dai, Yixuan Shao, Chenkai Mao +4
Nanophotonic freeform design has the potential to push the performance of optical components to new limits, but there remains a challenge to effectively perform optimization while…
A multi-agentic framework for real-time, autonomous freeform metasurface design
Robert Lupoiu, Yixuan Shao, Tianxiang Dai +3
Innovation in nanophotonics currently relies on human experts who synergize specialized knowledge in photonics and coding with simulation and optimization algorithms, entailing des…