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

2026-07-09

AI Summary

Traditional neural inverse design is constrained by fixed material vocabularies, predefined wavelength grids, and discretization of continuous variables, limiting its applicability to open-vocabulary materials, flexible spectral bands, and real-world fabrication requirements. This work proposes IrisFlow, a novel framework that, for the first time, treats wavelength-aware optical constants as input tokens and integrates a query-driven discrete-continuous joint flow-matching mechanism. At inference, IrisFlow dynamically accepts arbitrary target spectra, wavelength ranges, candidate materials, and layer counts, generalizing to unseen materials and spectral ranges beyond the training distribution without retraining. A single 136M-parameter model supports designs from 2 to 100 layers, achieves high-fidelity spectral reconstruction across a 224-task benchmark, maintains consistent accuracy on 15 previously unseen materials, and successfully fabricates four full-color radiative coolers with CIEDE2000 color differences of 3.1–5.2 and near-infrared reflectance of 93–95%.

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 optical coatings are an industrially important instance, coupling material sequence, layer thickness and wavelength-dependent response. We present IrisFlow, a query-based, open-vocabulary flow-matching framework instantiated in coatings: the target reflectance/transmittance spectrum, wavelength grid, candidate-material optical constants and layer count are supplied at query time. Candidate materials enter as wavelength-aware optical tokens rather than learned identities; material sequences are sampled by discrete flow matching over the query's candidate bank, thicknesses by continuous flow matching without discretization. A single 136M-parameter model designs 2-100-layer stacks. Across a 224-task benchmark it reconstructs in-distribution targets faithfully and retains same-order accuracy on a 15-material held-out bank without retraining; it reconstructs bands up to 1100 nm beyond its training envelope, designs against analytic application specifications and outperforms an autoregressive baseline on that baseline's material library. With optical constants calibrated to our deposition process, IrisFlow designs four color-displaying coolers, fabricated by ion-assisted evaporation: the three chromatic devices reach a CIEDE2000 color error of 3.1-5.2 while retaining 93-95% solar near-infrared reflectance, demonstrating open-vocabulary design carried through to fabricated coatings.

Problem

• inverse design
• optical coatings
• open-vocabulary
• multilayer
• flow matching

Innovation

• flow matching
• open-vocabulary design
• inverse design
• optical coatings
• discrete-continuous modeling