Inverse Design of Optical Multilayer Thin Films using Robust Masked Diffusion Models

• URL: http://arxiv.org/abs/2604.01106v1
• Date: Wed, 01 Apr 2026 16:33:05 GMT
• Title: Inverse Design of Optical Multilayer Thin Films using Robust Masked Diffusion Models
• Abstract summary: Inverse design of optical multilayer stacks seeks to infer layer materials, thicknesses, and ordering from a desired target spectrum.<n>We introduce textttOptoLlama, a masked diffusion language model for inverse thin-film design from optical spectra.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Inverse design of optical multilayer stacks seeks to infer layer materials, thicknesses, and ordering from a desired target spectrum. It is a long-standing challenge due to the large design space and non-unique solutions. We introduce \texttt{OptoLlama}, a masked diffusion language model for inverse thin-film design from optical spectra. Representing multilayer stacks as sequences of material-thickness tokens, \texttt{OptoLlama} conditions generation on reflectance, absorptance, and transmittance spectra and learns a probabilistic mapping from optical response to structure. Evaluated on a representative test set of 3,000 targets, \texttt{OptoLlama} reduces the mean absolute spectral error by 2.9-fold relative to a nearest-neighbor template baseline and by 3.45-fold relative to the state-of-the-art data-driven baseline, called \texttt{OptoGPT}. Case studies on designed and expert-defined targets show that the model reproduces characteristic spectral features and recovers physically meaningful stack motifs, including distributed Bragg reflectors. These results establish diffusion-based sequence modeling as a powerful framework for inverse photonic design.

Related papers

• Revisiting Spectral Representations in Generative Diffusion Models [98.43552218868837]
  Diffusion models have shown remarkable performance on diverse generation tasks.<n>Recent work finds that imposing representation alignment on the hidden states of diffusion networks can both facilitate training convergence and enhance sampling quality.<n>We investigate the connection between self-supervised spectral representation learning and diffusion generative models through a shared perspective on perturbation kernels.
  arXiv  Detail & Related papers  (2026-09-08T04:54:02Z)
• Spectral-Spatial Synergistic Guided Network for Hyperspectral Salient Object Detection [29.979358462284623]
  We propose a lightweight and efficient Spectral-Spatial Synergistic Guided Network (S3GNet) for object detection.<n>S3GNet builds a closed-loop information flow around spectrum robust modeling, cross-stream co-perception and multi-scale refinement decoding.<n> Experimental results show that S3GNet achieves superior performance in both computational efficiency and detection accuracy compared to existing methods.
  arXiv  Detail & Related papers  (2026-07-23T08:14:32Z)
• Inverse Design of Metasurface based Absorbers using Physics Guided Conditional Diffusion Models [4.875818256586011]
  Inverse design of metasurfaces for specific electromagnetic responses requires generating geometries that satisfy stringent spectral constraints.<n>We propose a physics guided condition quality enhanced diffusion framework for the inverse design of metasurface based absorbers.
  arXiv  Detail & Related papers  (2026-05-19T09:51:38Z)
• LD-SLRO: Latent Diffusion Structured Light for 3-D Reconstruction of Highly Reflective Objects [0.0]
  We propose a latent diffusion-based structured light for reflective objects (LD-SLRO)<n>Phase-shifted fringe images captured from highly reflective surfaces are first encoded to extract latent representations that capture surface reflectance characteristics.<n>Results demonstrate that the proposed method improves both fringe quality and 3-D reconstruction accuracy over state-of-the-art methods.
  arXiv  Detail & Related papers  (2026-02-05T08:24:38Z)
• Suppressing VLM Hallucinations with Spectral Representation Filtering [49.52703800684483]
  Vision-language models (VLMs) frequently produce hallucinations in the form of descriptions of objects, attributes, or relations that do not exist in the image.<n>We introduce Spectral Representation Filtering (SRF), a lightweight, training-free method to suppress such hallucinations by analyzing and correcting the covariance structure of the model's representations.
  arXiv  Detail & Related papers  (2025-11-15T13:49:27Z)
• MaterialRefGS: Reflective Gaussian Splatting with Multi-view Consistent Material Inference [83.38607296779423]
  We show that multi-view consistent material inference with more physically-based environment modeling is key to learning accurate reflections with Gaussian Splatting.<n>Our method faithfully recovers both illumination and geometry, achieving state-of-the-art rendering quality in novel views synthesis.
  arXiv  Detail & Related papers  (2025-10-13T13:29:20Z)
• DiffSpectra: Molecular Structure Elucidation from Spectra using Diffusion Models [68.19129717255053]
  We present DiffSpectra, a generative framework that formulates molecular structure elucidation as a conditional generation process.<n>Our experiments demonstrate that DiffSpectra accurately elucidates molecular structures, achieving 40.76% top-1 and 99.49% top-10 accuracy.
  arXiv  Detail & Related papers  (2025-07-09T13:57:20Z)
• Inverse Design of Diffractive Metasurfaces Using Diffusion Models [28.865660196923752]
  Metasurfaces are ultra-thin optical elements composed of engineered sub-wavelength structures that enable precise control of light.<n>In inverse design, determining a geometry that yields a desired optical response is challenging due to the complex, nonlinear relationship between structure and optical properties.<n>We address these challenges by integrating the generative capabilities of diffusion models into computational design.<n>We demonstrate our approach on the design of a spatially uniform intensity splitter and a polarization beam splitter, both produced with low error in under 30 minutes.
  arXiv  Detail & Related papers  (2025-06-26T20:10:30Z)
• Diffusion Model with Cross Attention as an Inductive Bias for Disentanglement [58.9768112704998]
  Disentangled representation learning strives to extract the intrinsic factors within observed data. We introduce a new perspective and framework, demonstrating that diffusion models with cross-attention can serve as a powerful inductive bias. This is the first work to reveal the potent disentanglement capability of diffusion models with cross-attention, requiring no complex designs.
  arXiv  Detail & Related papers  (2024-02-15T05:07:54Z)
• Learning transformer-based heterogeneously salient graph representation for multimodal remote sensing image classification [42.15709954199397]
  A transformer-based heterogeneously salient graph representation (THSGR) approach is proposed in this paper. First, a multimodal heterogeneous graph encoder is presented to encode distinctively non-Euclidean structural features from heterogeneous data. A self-attention-free multi-convolutional modulator is designed for effective and efficient long-term dependency modeling.
  arXiv  Detail & Related papers  (2023-11-17T04:06:20Z)
• Unsupervised Spectral Demosaicing with Lightweight Spectral Attention Networks [6.7433262627741914]
  This paper presents a deep learning-based spectral demosaicing technique trained in an unsupervised manner. The proposed method outperforms conventional unsupervised methods in terms of spatial distortion suppression, spectral fidelity, robustness, and computational cost.
  arXiv  Detail & Related papers  (2023-07-05T02:45:44Z)
• Protein Design with Guided Discrete Diffusion [67.06148688398677]
  A popular approach to protein design is to combine a generative model with a discriminative model for conditional sampling. We propose diffusioN Optimized Sampling (NOS), a guidance method for discrete diffusion models. NOS makes it possible to perform design directly in sequence space, circumventing significant limitations of structure-based methods.
  arXiv  Detail & Related papers  (2023-05-31T16:31:24Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.