Chenkai Mao

All Publications

• A multi-agentic framework for real-time, autonomous freeform metasurface design. Science advances Lupoiu, R., Shao, Y., Dai, T., Mao, C., Edée, K., Fan, J. A. 2025; 11 (44): eadx8006

  Abstract

  Innovation in nanophotonics currently relies on human experts who synergize specialized knowledge in photonics and coding with simulation and optimization algorithms, entailing design cycles that are time-consuming, computationally demanding, and frequently suboptimal. We introduce MetaChat, a multi-agentic design framework that can translate semantically described photonic design goals into high-performance, freeform device layouts in an automated, nearly real-time manner. Multistep reasoning is enabled by our Agentic Iterative Monologue paradigm, which coherently interfaces agents with code-based tools, other specialized agents, and human designers. Design acceleration is facilitated by Feature-wise Linear Modulation-conditioned Maxwell surrogate solvers that support the generalized evaluation of metasurface structures. We use freeform dielectric metasurfaces as a model system and demonstrate with MetaChat the design of multiobjective, multiwavelength metasurfaces orders of magnitude faster than conventional methods. These concepts present a scientific computing blueprint for using specialist design agents, surrogate solvers, and human interactions to drive multiphysics innovation and discovery.

  View details for DOI 10.1126/sciadv.adx8006

  View details for PubMedID 41171904

• Shaping freeform nanophotonic devices with geometric neural parameterization NPJ COMPUTATIONAL MATERIALS Dai, T., Shao, Y., Mao, C., Wu, Y., Azzouz, S., Zhou, Y., Fan, J. A. 2025; 11 (1)

  View details for DOI 10.1038/s41524-025-01752-w

  View details for Web of Science ID 001546112400001

• Inverse-designed metasurfaces with facile fabrication parameters JOURNAL OF OPTICS Zhou, Y., Shao, Y., Mao, C., Fan, J. A. 2024; 26 (5)

  View details for DOI 10.1088/2040-8986/ad33a7

  View details for Web of Science ID 001188548100001

• Large-Area, High-Numerical-Aperture, Freeform Metasurfaces LASER & PHOTONICS REVIEWS Zhou, Y., Mao, C., Gershnabel, E., Chen, M., Fan, J. A. 2024

  View details for DOI 10.1002/lpor.202300988

  View details for Web of Science ID 001163678600001

• Towards General Neural Surrogate Solvers with Specialized Neural Accelerators Proceedings of the 41st International Conference on Machine Learning Mao, C., Lupoiu, R., Dai, T., Chen, M., Fan, J. 2024
• Reparameterization Approach to Gradient-Based Inverse Design of Three-Dimensional Nanophotonic Devices ACS PHOTONICS Gershnabel, E., Chen, M., Mao, C., Wang, E. W., Lalanne, P., Fan, J. A. 2022

  View details for DOI 10.1021/acsphotonics.2c01160

  View details for Web of Science ID 000874561200001

• High Speed Simulation and Freeform Optimization of Nanophotonic Devices with Physics-Augmented Deep Learning ACS PHOTONICS Chen, M., Lupoiu, R., Mao, C., Huang, D., Jiang, J., Lalanne, P., Fan, J. A. 2022

  View details for DOI 10.1021/acsphotonics.2c00876

  View details for Web of Science ID 000848111900001

• WaveY-Net: Physics-Augmented Deep Learning for High-Speed Electromagnetic Simulation and Optimization Chen, M., Lupoiu, R., Mao, C., Huang, D., Jiang, J., Lalanne, P., Fan, J. A. edited by Chang-Hasnain, C. J., Fan, J. A., Zhou, W. SPIE-INT SOC OPTICAL ENGINEERING. 2022

  View details for DOI 10.1117/12.2612418

  View details for Web of Science ID 000836330700011