纳米光子学
反向
计算机科学
生成语法
生成设计
反问题
多模态
人工智能
扩散
设计要素和原则
作者
Yuheng Chen,Rohan Ojha,Vaishnavi Iyer,Alexander V. Kildishev,Vladimir M. Shalaev,Alexandra E. Boltasseva
出处
期刊:Conference on Lasers and Electro-Optics
日期:2026-01-01
卷期号:: JTU.66-JTU.66
标识
DOI:10.1364/cleo_at.2026.jtu.66
摘要
A physics-conditioned, multimodal LLM-powered stable diffusion model enables generative nanophotonics inverse design guided by optical performance and prompts for geometry and fabrication. This approach provides controllable, fabrication-aware designs of high-performance nanophotonics structures directly from natural-language prompts.
科研通智能强力驱动
Strongly Powered by AbleSci AI