PulseAugur
实时 20:34:09
English(EN) Joint Discrete-Continuous Flow Matching for Open-Vocabulary Inverse Design of Multilayer Optical Coatings

IrisFlow框架实现了光学涂层的开放词汇设计

研究人员开发了IrisFlow,一个用于通过基于查询的开放词汇方法设计多层光学涂层的新型框架。该方法允许在查询时指定目标光谱、材料光学常数和层数,超越了固定的词汇表和离散化的连续变量。该系统由一个1.36亿参数模型驱动,展示了设计复杂涂层堆栈的能力,并已成功应用于制造具有低色差和高太阳反射率的显示冷却器。 AI

影响 这项研究通过实现更灵活高效的逆向设计流程,有望加速先进光学材料的设计和制造。

排序理由 该集群包含一篇学术论文,详细介绍了一种新的光学涂层设计方法和模型。

在 arXiv cs.LG 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →

IrisFlow框架实现了光学涂层的开放词汇设计

报道来源 [2]

  1. arXiv cs.LG TIER_1 English(EN) · Zhiyi Li, Yuheng Jin, Yidan Huang, Nan Chen, Hongyan Fu, Yikun Bu ·

    Joint Discrete-Continuous Flow Matching for Open-Vocabulary Inverse Design of Multilayer Optical Coatings

    arXiv:2607.08392v1 Announce Type: cross Abstract: Amortized neural inverse design typically remains closed-world: component choices are fixed vocabulary tokens, coordinate grids are frozen at training time, and continuous variables are discretized into sequence tokens. Multilayer…

  2. arXiv cs.LG TIER_1 English(EN) · Yikun Bu ·

    Joint Discrete-Continuous Flow Matching for Open-Vocabulary Inverse Design of Multilayer Optical Coatings

    Amortized neural inverse design typically remains closed-world: component choices are fixed vocabulary tokens, coordinate grids are frozen at training time, and continuous variables are discretized into sequence tokens. Multilayer optical coatings are an industrially important in…