Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.
Advertisement
Nature Computational Science (2026)
Information metamaterials are digital coding electromagnetic structures that connect wave control with information processing, offering programmable routes to beam shaping, focusing and holographic imaging. Their inverse design remains challenging because both meta-atoms and spatial coding arrays must be selected from a vast combinatorial space, and existing optimization or learning methods are often tailored to specific tasks, bit resolutions or field patterns. Here we show a generative model for information metamaterial design that learns a shared design prior and transfers it across diverse electromagnetic functions. The model combines a pretrained diffusion backbone with lightweight functionality-oriented adapters, enabling the generation of multibit meta-atoms with prescribed responses and nonuniform arrays for beam steering, near-field focusing and holography. Numerical simulations and experiments validate high-performance meta-atoms and functional 1-bit and 3-bit meta-arrays. For holographic design, the model reaches Gerchberg–Saxton-level fidelity while reducing runtime by over three orders of magnitude, establishing a scalable route to information-metamaterial discovery.
This is a preview of subscription content, access via your institution
Access Nature and 54 other Nature Portfolio journals
Get Nature+, our best-value online-access subscription
$32.99 / 30 days
cancel any time
Subscribe to this journal
Receive 12 digital issues and online access to articles
$119.00 per year
only $9.92 per issue
Buy this article
USD 39.95
Prices may be subject to local taxes which are calculated during checkout
Source Data for Figs. 2–5 is available with this Article. The data are available via Code Ocean capsule at https://doi.org/10.24433/CO.0515873.v2 (ref. 50).
The source codes used in this study are available via Code Ocean capsule at https://doi.org/10.24433/CO.0515873.v2 (ref. 50).
Abramson, J. et al. Accurate structure prediction of biomolecular interactions with AlphaFold 3. Nature 630, 493–500 (2024).
Article Google Scholar
Jumper, J. et al. Highly accurate protein structure prediction with AlphaFold. Nature 596, 583–589 (2021).
Article Google Scholar
Zeni, C. et al. A generative model for inorganic materials design. Nature 639, 624–632 (2025).
Article Google Scholar
Liu, T., Ou, J.-Y., MacDonald, K. F. & Zheludev, N. I. Photonic metamaterial analogue of a continuous time crystal. Nat. Phys. 19, 986–991 (2023).
Article Google Scholar
Choi, M. et al. A terahertz metamaterial with unnaturally high refractive index. Nature 470, 369–373 (2011).
Article Google Scholar
Zhao, T. et al. Modular chiral origami metamaterials. Nature 640, 931–940 (2025).
Article Google Scholar
Zhang, R.-Y. et al. Bulk–spatiotemporal vortex correspondence in gyromagnetic zero-index media. Nature 641, 1142–1148 (2025).
Article Google Scholar
Veenstra, J. et al. Non-reciprocal topological solitons in active metamaterials. Nature 627, 528–533 (2024).
Article Google Scholar
Lim, D. D. et al. A tunable metamaterial microwave absorber inspired by chameleon’s color-changing mechanism. Sci. Adv. 11, eads3499 (2025).
Article Google Scholar
Zhang, X., Kim, E., Mark, D. K., Choi, S. & Painter, O. A superconducting quantum simulator based on a photonic-bandgap metamaterial. Science 379, 278–283 (2023).
Article Google Scholar
Eidini, M. & Paulino, G. H. Unraveling metamaterial properties in zigzag-base folded sheets. Sci. Adv. 1, e1500224 (2015).
Article Google Scholar
Larouche, S., Tsai, Y.-J., Tyler, T., Jokerst, N. M. & Smith, D. R. Infrared metamaterial phase holograms. Nat. Mater. 11, 450–454 (2012).
Article Google Scholar
Lier, E., Werner, D. H., Scarborough, C. P., Wu, Q. & Bossard, J. A. An octave-bandwidth negligible-loss radiofrequency metamaterial. Nat. Mater. 10, 216–222 (2011).
Article Google Scholar
Yang, W. et al. Observation of optical gyromagnetic properties in a magneto-plasmonic metamaterial. Nat. Commun. 13, 1719 (2022).
Article Google Scholar
Lin, D., Fan, P., Hasman, E. & Brongersma, M. L. Dielectric gradient metasurface optical elements. Science 345, 298–302 (2014).
Article Google Scholar
Kildishev, A. V., Boltasseva, A. & Shalaev, V. M. Planar photonics with metasurfaces. Science 339, 1232009 (2013).
Article Google Scholar
Ni, X., Wong, Z. J., Mrejen, M., Wang, Y. & Zhang, X. An ultrathin invisibility skin cloak for visible light. Science 349, 1310–1314 (2015).
Article Google Scholar
Cui, T. J., Qi, M. Q., Wan, X., Zhao, J. & Cheng, Q. Coding metamaterials, digital metamaterials and programmable metamaterials. Light Sci. Appl. 3, e218 (2014).
Article Google Scholar
He, Q., Ferracin, S. & Raney, J. R. Programmable responsive metamaterials for mechanical computing and robotics. Nat. Comput. Sci. 4, 567–573 (2024).
Article Google Scholar
Li, L. et al. Electromagnetic reprogrammable coding-metasurface holograms. Nat. Commun. 8, 197 (2017).
Article Google Scholar
You, J. W. et al. Reprogrammable plasmonic topological insulators with ultrafast control. Nat. Commun. 12, 5468 (2021).
Article Google Scholar
Xu, H. et al. Two-dimensional and high-order directional information modulations for secure communications based on programmable metasurface. Nat. Commun. 15, 6140 (2024).
Article Google Scholar
Ma, Q. et al. Smart metasurface with self-adaptively reprogrammable functions. Light Sci. Appl. 8, 98 (2019).
Article Google Scholar
Hu, S. et al. Electromagnetic metamaterial agent. Light Sci. Appl. 14, 12 (2025).
Article Google Scholar
Li, W. et al. Intelligent metasurface system for automatic tracking of moving targets and wireless communications based on computer vision. Nat. Commun. 14, 989 (2023).
Article Google Scholar
Zhang, L. et al. Space-time-coding digital metasurfaces. Nat. Commun. 9, 4334 (2018).
Article Google Scholar
Wu, G.-B., Dai, J. Y., Cheng, Q., Cui, T. J. & Chan, C. H. Sideband-free space–time-coding metasurface antennas. Nat. Electron. 5, 808–819 (2022).
Article Google Scholar
Ke, J. C. et al. Frequency-modulated continuous waves controlled by space-time-coding metasurface with nonlinearly periodic phases. Light Sci. Appl. 11, 273 (2022).
Article Google Scholar
Zhang, L. et al. A wireless communication scheme based on space- and frequency-division multiplexing using digital metasurfaces. Nat. Electron. 4, 218–227 (2021).
Article Google Scholar
Wu, G.-B. et al. A synthetic moving-envelope metasurface antenna for independent control of arbitrary harmonic orders. Nat. Commun. 15, 7202 (2024).
Article Google Scholar
Qian, C., Kaminer, I. & Chen, H. A guidance to intelligent metamaterials and metamaterials intelligence. Nat. Commun. 16, 1154 (2025).
Article Google Scholar
Liu, Z., Zhu, D., Rodrigues, S. P., Lee, K.-T. & Cai, W. Generative model for the inverse design of metasurfaces. Nano Lett. 18, 6570–6576 (2018).
Article Google Scholar
Jiang, J. et al. Free-form diffractive metagrating design based on generative adversarial networks. ACS Nano 13, 8872–8878 (2019).
Article Google Scholar
Zhu, R. et al. Phase-to-pattern inverse design paradigm for fast realization of functional metasurfaces via transfer learning. Nat. Commun. 12, 2974 (2021).
Article Google Scholar
Liu, C., Yu, W. M., Ma, Q., Li, L. & Cui, T. J. Intelligent coding metasurface holograms by physics-assisted unsupervised generative adversarial network. Photon. Res. 9, B159–B167 (2021).
Article Google Scholar
Ma, T., Tobah, M., Wang, H. & Guo, L. J. Benchmarking deep learning-based models on nanophotonic inverse design problems. Opto-Electron. Sci. 1, 210012-210011–210012-210015 (2022).
Article Google Scholar
Su, J. L. et al. Multi-dimensional multiplexed metasurface for multifunctional near-field modulation by physics-driven intelligent design. Adv. Sci. 12, 2503899 (2025).
Article Google Scholar
Zhang, J. et al. Physics-driven machine-learning approach incorporating temporal coupled mode theory for intelligent design of metasurfaces. IEEE Trans. Microwave Theory Tech. 71, 2875–2887 (2023).
Article Google Scholar
Metamaterials design via and for computation. Nat. Comput. Sci. 4, 543–544 (2024).
Bonfanti, S. et al. Computational design of mechanical metamaterials. Nat. Comput. Sci. 4, 574–583 (2024).
Article Google Scholar
Dudte, L. H., Choi, G. P. T., Becker, K. P. & Mahadevan, L. An additive framework for kirigami design. Nat. Comput. Sci. 3, 443–454 (2023).
Article Google Scholar
Li, E. et al. Current-diffusion model for metasurface structure discoveries with spatial-frequency dynamics. Nat. Mach. Intell. 8, 59–69 (2026).
Article Google Scholar
Chao, Q. et al. Autonomous aeroamphibious invisibility cloak with stochastic-evolution learning. Adv. Photon. 6, 016001 (2024).
Google Scholar
Lu, H. et al. Eye accommodation-inspired neuro-metasurface focusing. Nat. Commun. 14, 3301 (2023).
Article Google Scholar
Zhu, R. et al. Deep-learning-empowered holographic metasurface with simultaneously customized phase and amplitude. ACS Appl. Mater. Interfaces 14, 48303–48310 (2022).
Article Google Scholar
Hao, H., Zheng, S., Tang, Y. & Ran, X. Broadband transmissive amplitude-and-phase metasurface for vortex beam generation and hologram. Phys. Lett. A 434, 128036 (2022).
Article Google Scholar
Ren, H. et al. Complex-amplitude metasurface-based orbital angular momentum holography in momentum space. Nat. Nanotechnol. 15, 948–955 (2020).
Article Google Scholar
Gopakumar, M. et al. Full-colour 3D holographic augmented-reality displays with metasurface waveguides. Nature 629, 791–797 (2024).
Article Google Scholar
Hu, Y. et al. 3D-Integrated metasurfaces for full-colour holography. Light Sci. Appl. 8, 86 (2019).
Article Google Scholar
You, J. W. & Cui, T. J. Generative model for information metamaterial design. Code Ocean https://doi.org/10.24433/CO.0515873.v2 (2026).
Article Google Scholar
Download references
The work was supported by the National Natural Science Foundation of China (grant nos. 62288101, 62301149 and 62401132), the National Key Research and Development Program of China (grant no. 2023YFB3813100), the Jiangsu Planned Projects for Postdoctoral Research Fund (grant no. 2023ZB318), the Independent Research Fund of the State Key Laboratory of Millimeter Waves (grant no. Z202602-01) and the Special Fund for Key Basic Research in Jiangsu Province (grant nos. BK20212002, BK20243015 and BK20230820).
These authors contributed equally: Junming Hou, Long Chen, Xuan Zheng, Jia Wei Wu, Jian Wei You.
State Key Laboratory of Millimeter Waves, Southeast University, Nanjing, China
Junming Hou, Long Chen, Xuan Zheng, Jia Wei Wu, Jian Wei You, Zi Xuan Cai, Jiahan Huang, Chenxu Wu, Jian Lin Su, Jia Nan Zhang & Tie Jun Cui
School of Information Science and Engineering, Southeast University, Nanjing, China
Junming Hou, Long Chen, Xuan Zheng, Jia Wei Wu, Jian Wei You, Zi Xuan Cai, Jiahan Huang, Chenxu Wu, Jian Lin Su, Jia Nan Zhang & Tie Jun Cui
State Key Laboratory of Photonics and Communications, Peking University, Beijing, China
Lianlin Li
Institute of Electromagnetic Space, Southeast University, Nanjing, China
Tie Jun Cui
Suzhou Laboratory, Suzhou, China
Tie Jun Cui
PubMed Google Scholar
PubMed Google Scholar
PubMed Google Scholar
PubMed Google Scholar
PubMed Google Scholar
PubMed Google Scholar
PubMed Google Scholar
PubMed Google Scholar
PubMed Google Scholar
PubMed Google Scholar
PubMed Google Scholar
PubMed Google Scholar
J. Hou, L.C., X.Z., J.W.Y. and T.J.C. conceived the study, implemented the methods, performed computational experiments and wrote the paper. J. Hou, X.Z., J.W.W., J.N.Z. and J.W.Y. helped with the development of functional adapters, model training and the video illustration. Z.X.C., L.C., J.L.S., J. Huang, J.W.Y., L.L. and T.J.C. assisted with the experimental verification and preparation of the Supplementary Information. C.W., L.C., J.W.Y. and T.J.C. contributed to the figure visualizations.
Correspondence to Jian Wei You, Jia Nan Zhang or Tie Jun Cui.
The authors declare no competing interests.
Nature Computational Science thanks Yandong Li, Juan Manuel Restrepo-Florez and the other, anonymous, reviewer(s) for their contribution to the peer review of this work. Primary Handling Editor: Jie Pan, in collaboration with the Nature Computational Science team. Peer reviewer reports are available.
Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Supplementary Notes 1–19, Figs. 1–50, Tables 1–6, Equations 1–36 and references.
Source data for Fig. 2c–f. Figure 2c is based on the generated data collected during the inference stage. Figure 2d presents two results of conditional generation. Figure 2e includes two scatter plots corresponding to the two generation conditions, comparing the properties of the dataset and the generated samples. Figure 2f shows two confusion matrices that evaluate the model’s performance in 3-bit meta-atom generation.
Source data for Fig. 3b,c,d,f. Figure 3b shows a statistical distribution of the results generated from 100 simulations for a specific beam-forming target. Figures 3c,d present box plots of the statistical distributions of digit counts for the generated 1-bit and 3-bit far-field beam-forming coding patterns. Figure 3f shows a comparison of experimental and simulated results for beam-forming under a specific target.
Source data for Fig. 4b,c,d,f. Figure 4b shows a statistical distribution of the results generated from 100 simulations for a specific focusing target. Figure 4c,d present box plots of the statistical distributions of digit counts for the generated 1-bit and 3-bit near-field focusing coding patterns. Figure 4f shows a comparison of experimental and simulated results for near-field focusing under a specific target.
Source data for Fig. 5b,c,d,f. Figure 5b shows the statistical distribution of results obtained from 100 generations for a specific holographic target, as well as the average generation metrics for 20 different targets. Figure 5c,d shows box plots of the statistical distributions of digit counts for the generated 1-bit and 3-bit near-field holographic coding patterns. Figure 5f shows a comparison of experimental and simulated results for holography under a specific target.
Source data for Fig. 6a–c. Figure 6a,b shows the PSNR and SSIM values versus time for different methods, respectively. Figure 6c shows the PSNR versus time and the SSIM versus time for different methods.
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
Reprints and permissions
Hou, J., Chen, L., Zheng, X. et al. Generative model for information metamaterial design. Nat Comput Sci (2026). https://doi.org/10.1038/s43588-026-01025-6
Download citation
Received:
Accepted:
Published:
Version of record:
DOI: https://doi.org/10.1038/s43588-026-01025-6
Anyone you share the following link with will be able to read this content:
Sorry, a shareable link is not currently available for this article.
Provided by the Springer Nature SharedIt content-sharing initiative
Advertisement
Nature Computational Science (Nat Comput Sci)
ISSN 2662-8457 (online)
© 2026 Springer Nature Limited
Sign up for the Nature Briefing: AI and Robotics newsletter — what matters in AI and robotics research, free to your inbox weekly.