MOCLIP (Metasurface Optics Contrastive Learning Pretrained) is a nanophotonic foundation model that unifies metasurface geometry and spectra in a shared latent space using contrastive learning on an ImageNet‑1K–sized experimental dataset. It enables high‑throughput zero‑shot inverse design, predicting 0.2 million samples per second and allowing the design of a full 4‑inch wafer of high‑density metasurfaces in minutes. The model also supports generative latent‑space optimization with 97 % accuracy and demonstrates an optical information storage concept achieving 0.1 Gbit/mm², six times higher than commercial optical media.
By S. Rodionov, A. Burguete-Lopez, M. Makarenko, Q. Wang, F. Getman, A. Fratalocchi
The paper presents a collaborative on‑sensor array camera that uses a distributed meta‑optics learning method to jointly optimize a 100‑million‑nanopost metasurface array for broadband visible imaging. By training the array end‑to‑end with a learned meta‑atom proxy and a parallax‑aware, noise‑aware reconstruction algorithm, the design overcomes the wavelength‑dependent limitations of traditional metalenses. Experimental results show that the camera delivers consistent image quality across varying scene illumination spectra without relying on generative reconstruction.
By Jipeng Sun, Kaixuan Wei, Thomas Eboli, Congli Wang, Cheng Zheng, Zhihao Zhou, Arka Majumdar, Wolfgang Heidrich, Felix Heide
arXiv:2602. 08406v2 Announce Type: replace-cross Abstract: The prediction of electromagnetic spectra for MXene-based solar absorbers, where MXenes are a family of two-dimensional transition metal carbides and nitrides, is a computationally intensive task traditionally addressed using full-wave solvers.
By Shujaat Khan, Waleed Iqbal Waseer, Muhammad Shahid Jabbar
Metasurfaces enable precise manipulation of electromagnetic waves for applications such as beam steering, sensing, and stealth technology. However, inverse design of metasurfaces with targeted EM responses remains challenging due to the computational expense of iterative full wave simulation driven optimization and the limited conditioning fidelity and diversity of existing generative approaches.
The paper presents a method for training single‑step neural surrogates that can handle wave‑scattering problems with tens of thousands of controllable variables. By dynamically generating training examples that highlight surrogate errors and using a replay dataset with normalization, the authors achieve a surrogate that accurately simulates two‑dimensional wave scattering for up to 41,772 variables and generalizes to over 3 million variables without retraining. The surrogate is applied to forward simulations and inverse design of freeform beam splitters and gradient‑index lenses, achieving speedups up to 26.5× compared to traditional FDTD methods.
By Charles Dove, Laura Waller
The paper presents a method for training single‑step neural surrogates that can handle wave‑scattering inverse problems with tens of thousands of controllable variables. By dynamically generating training examples through gradient ascent and using a replay dataset with normalization, the authors achieve a surrogate that accurately models two‑dimensional wave scattering for up to 41,772 variables and can generalize to over 3 million variables without retraining. The surrogate demonstrates comparable or better performance than traditional FDTD simulations for large‑scale forward simulations and inverse design of photonic devices, achieving speedups up to 26.5×.
The paper proposes using ultrathin metalenses to physically encode metric depth cues into two polarized optical wavefronts, enabling accurate monocular depth estimation. By aligning a pretrained depth foundation model with these optical signals through direct fine‑tuning, and by creating a simulation pipeline to generate realistic metalens responses from RGB‑D data, the authors bridge the gap between nanophotonics and learned depth priors. Experiments show that this method surpasses conventional monocular metric depth estimation and depth‑from‑defocus baselines.
By Bingxuan Li, Jiahao Wu, Yuan Xu, Zezheng Zhu, Yunxiang Zhang, Kenneth Chen, Yanqi Liang, Nanfang Yu, Qi Sun
arXiv:2604. 02429v2 Announce Type: replace-cross Abstract: Convolutional neural networks (CNNs) have transformed image processing, but the energy consumption and inference latency of electronic based implementations remain fundamental bottlenecks.
By Saurabh Ranjan, Sonika Thakral, Amit Sehgal
The review examines how Large Language Models (LLMs) enhance nanophotonics design by providing semantic interfaces, code generation, and tool orchestration. It traces the evolution from classical neural networks to transformer-based models and categorizes LLM applications into surrogate models that map structure to spectrum and agentic systems that generate code and orchestrate simulations for closed-loop optimization. The article also highlights potential cross-disciplinary uses of LLMs in materials science and wireless communications, and envisions future multimodal foundation models that actively collaborate in autonomous scientific discovery.
By Huanshu Zhang, Kegeng Tang, Lei Kang, Sawyer D. Campbell, Zihao Wang, Douglas H. Werner
The paper presents a machine‑learning framework for reconstructing absorption and scattering coefficients in bilayered biological media from single‑distance, time‑resolved reflectance data. By training on a synthetic dataset generated with exact Monte Carlo simulations, the method outperforms traditional diffusion‑equation‑based inverse solvers in both speed and accuracy. It also estimates the dimensionality of the parameter space without prior knowledge of the number of layers, and suggests that future work could further improve accuracy using multi‑distance data.
By Caterina Amendola, Giulia Maffeis, Lorenzo Buffoni, Lorenzo Chicchi, Francesco Coghi, Duccio Fanelli, Raffaele Marino, Fabrizio Martelli, Riccardo Paoli, Lorenzo Pattelli, Lorenzo Spinelli
arXiv:2606. 09266v1 Announce Type: cross Abstract: Acoustic metamaterial (AMM) inverse design is particularly challenging for broadband target responses due to acoustic dispersion: a structure that matches the desired response at one frequency may deviate at others, and modifying geometry to improve one sub-band often perturbs neighboring sub-bands.
By Yijie Li, Jiahao Xu, Ching-Chih Tsao, Lili Qiu, Jingxian Wang
The paper presents iPINN, an inverse physics‑informed neural network designed for broadband coherent anti‑Stokes Raman spectroscopy (BCARS) phase retrieval. iPINN predicts Lorentzian peak parameters from raw BCARS spectra and reconstructs the resonant susceptibility using a differentiable analytical forward model, employing a transformer encoder and a multi‑view consistency loss to handle varying non‑resonant background conditions. On a public benchmark it achieves the lowest mean absolute error (0.016) compared to other methods, and demonstrates depth‑invariant accuracy across multiple solvents and focal positions.
By Ravi Teja Vulchi, Carl Messerschmidt, Mohammadsadegh Vafaeinezhad, Rajendhar Junjuri, Tobias Meyer-Zedler, Juergen Popp, Thomas Bocklitz