{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T19:43:29Z","timestamp":1792784609283,"version":"4.5.0"},"reference-count":39,"publisher":"American Chemical Society (ACS)","issue":"36","license":[{"start":{"date-parts":[[2026,8,28]],"date-time":"2026-08-28T00:00:00Z","timestamp":1787875200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,8,28]],"date-time":"2026-08-28T00:00:00Z","timestamp":1787875200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,8,28]],"date-time":"2026-08-28T00:00:00Z","timestamp":1787875200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-045"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2024YFB4610700"],"award-info":[{"award-number":["2024YFB4610700"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["WK2090000081"],"award-info":[{"award-number":["WK2090000081"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["WK2090000088"],"award-info":[{"award-number":["WK2090000088"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"name":"University of Science and Technology of China-Southwest University of Science and Technology Counterpart Cooperation and Development Joint Fund","award":["24LHJJ08"],"award-info":[{"award-number":["24LHJJ08"]}],"id":[{"id":"https:\/\/ror.org\/04d996474","id-type":"ROR","asserted-by":"crossref"}]},{"name":"CAS Project for Young Scientists in Basic Research","award":["YSBR-049"],"award-info":[{"award-number":["YSBR-049"]}]},{"name":"National Natural Science Foundation of China (NSFC)","award":["52375582"],"award-info":[{"award-number":["52375582"]}],"id":[{"id":"https:\/\/ror.org\/01h0zpd94","id-type":"ROR","asserted-by":"crossref"}]},{"name":"National Natural Science Foundation of China (NSFC)","award":["62475252"],"award-info":[{"award-number":["62475252"]}],"id":[{"id":"https:\/\/ror.org\/01h0zpd94","id-type":"ROR","asserted-by":"crossref"}]},{"name":"National Natural Science Foundation of China (NSFC)","award":["62575274"],"award-info":[{"award-number":["62575274"]}],"id":[{"id":"https:\/\/ror.org\/01h0zpd94","id-type":"ROR","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,9,16]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Diffractive deep neural networks (D2NNs) provide a promising pathway toward high-speed, energy-efficient optical computing. However, a substantial discrepancy between simulation and experiment remains when devices are fabricated by two-photon polymerization (TPP) for visible\/near-infrared operation. This discrepancy is primarily due to fabrication constraints. In particular, the finite voxel size of the writing focus and the layer-by-layer slicing quantization attenuate high-spatial-frequency phase features and distort the designed wavefront. Here, a fabrication-aware training (FAT) strategy is introduced to incorporate these dominant constraints into the optimization loop through a differentiable model, thereby improving the experimental performance of two-photon polymerized D2NNs. In a handwritten digit recognition task, FAT increases the average experimental energy concentration ratio (ECR) from 6.15% to 11.50%. This reduces the simulation-to-experiment discrepancy by 79.03% while preserving the classification accuracy. These results demonstrate that fabrication-aware optimization substantially improves the functional fidelity of micro\/nanoscale diffractive optical computing devices.<\/jats:p>","DOI":"10.1021\/acs.nanolett.6c01607","type":"journal-article","created":{"date-parts":[[2026,9,2]],"date-time":"2026-09-02T03:44:54Z","timestamp":1788320694000},"page":"11979-11987","source":"Crossref","is-referenced-by-count":0,"title":["Fabrication-Aware\nTraining for Two-Photon Polymerized\nDiffractive Deep Neural Networks"],"prefix":"10.1021","volume":"26","author":[{"given":"Jiale","family":"Yao","sequence":"first","affiliation":[{"name":"University of Science and Technology of China , , ,","place":["Hefei, China, 230027"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiabin","family":"Bi","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China , , ,","place":["Hefei, China, 230027"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuhang","family":"Xue","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China , , ,","place":["Hefei, China, 230027"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liqun","family":"Xu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China , , ,","place":["Hefei, China, 230027"]},{"name":"Circuit Fabology Microelectronics Equipment Co., Ltd. , ,","place":["Hefei, China, 230088"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhaohui","family":"Ye","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China , , ,","place":["Hefei, China, 230027"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haowen","family":"Liu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China , , ,","place":["Hefei, China, 230027"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bowen","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China , , ,","place":["Hefei, China, 230027"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jincheng","family":"Ni","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China , , ,","place":["Hefei, China, 230027"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3950-6212","authenticated-orcid":true,"given":"Jiawen","family":"Li","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China , , ,","place":["Hefei, China, 230027"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0623-1515","authenticated-orcid":true,"given":"Dong","family":"Wu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China , , ,","place":["Hefei, China, 230027"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1964-0043","authenticated-orcid":true,"given":"Yanlei","family":"Hu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China , , ,","place":["Hefei, China, 230027"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"316","published-online":{"date-parts":[[2026,8,28]]},"reference":[{"issue":"7905","key":"2026091608072017800_cit1","doi-asserted-by":"publisher","first-page":"255","DOI":"10.1038\/s41586-021-04362-w","article-title":"Brain-Inspired Computing Needs a Master Plan","volume":"604","author":"Mehonic","year":"2022","journal-title":"Nature"},{"key":"2026091608072017800_cit2","doi-asserted-by":"publisher","first-page":"499","DOI":"10.1038\/s42254-020-0208-2","article-title":"Physics for Neuromorphic\nComputing","volume":"2","author":"Markovic\u0301","year":"2020","journal-title":"Nature Reviews Physics"},{"key":"2026091608072017800_cit3","doi-asserted-by":"publisher","first-page":"1611658","DOI":"10.3389\/fsci.2025.1611658","article-title":"Breaking the Memory\nWall: Next-Generation Artificial Intelligence Hardware","volume":"3","author":"Roy","year":"2025","journal-title":"Frontiers in Science"},{"key":"2026091608072017800_cit4","doi-asserted-by":"publisher","first-page":"arXiv:2504.07139","DOI":"10.48550\/arXiv.2504.07139","article-title":"Artificial\nIntelligence Index Report 2025","author":"Maslej","year":"2025","journal-title":"arXiv Preprints"},{"issue":"1","key":"2026091608072017800_cit5","doi-asserted-by":"publisher","first-page":"263","DOI":"10.1038\/s41377-024-01590-3","article-title":"Optical Neural Networks:\nProgress and Challenges","volume":"13","author":"Fu","year":"2024","journal-title":"Light: Science &\nApplications"},{"issue":"2","key":"2026091608072017800_cit6","doi-asserted-by":"publisher","first-page":"102","DOI":"10.1038\/s41566-020-00754-y","article-title":"Photonics for Artificial\nIntelligence and Neuromorphic Computing","volume":"15","author":"Shastri","year":"2021","journal-title":"Nat.\nPhotonics"},{"issue":"1","key":"2026091608072017800_cit7","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1186\/s43074-021-00026-0","article-title":"Research Progress in\nOptical Neural Networks:\nTheory, Applications and Developments","volume":"2","author":"Liu","year":"2021","journal-title":"PhotoniX"},{"issue":"7","key":"2026091608072017800_cit8","doi-asserted-by":"publisher","first-page":"2001","DOI":"10.1021\/acsphotonics.2c01516","article-title":"Integrated Photonic\nNeural Networks: Opportunities and Challenges","volume":"10","author":"Liao","year":"2023","journal-title":"ACS Photonics"},{"issue":"12","key":"2026091608072017800_cit9","doi-asserted-by":"publisher","first-page":"1335","DOI":"10.1038\/s41566-024-01567-z","article-title":"Single-Chip Photonic\nDeep Neural Network with Forward-Only Training","volume":"18","author":"Bandyopadhyay","year":"2024","journal-title":"Nat. Photonics"},{"issue":"6406","key":"2026091608072017800_cit10","doi-asserted-by":"publisher","first-page":"1004","DOI":"10.1126\/science.aat8084","article-title":"All-Optical Machine\nLearning Using Diffractive Deep Neural Networks","volume":"361","author":"Lin","year":"2018","journal-title":"Science"},{"issue":"2","key":"2026091608072017800_cit11","doi-asserted-by":"publisher","DOI":"10.1063\/5.0191977","article-title":"Diffractive\nDeep Neural Networks: Theories, Optimization, and Applications","volume":"11","author":"Chen","year":"2024","journal-title":"Applied Physics Reviews"},{"issue":"1","key":"2026091608072017800_cit12","doi-asserted-by":"publisher","first-page":"1525","DOI":"10.1038\/s41467-024-45982-w","article-title":"Diffractive Optical\nComputing in Free Space","volume":"15","author":"Hu","year":"2024","journal-title":"Nat. Commun."},{"issue":"2","key":"2026091608072017800_cit13","doi-asserted-by":"publisher","DOI":"10.29026\/oea.2024.230005","article-title":"Pluggable\nMultitask Diffractive Neural Networks Based on Cascaded\nMetasurfaces","volume":"7","author":"He","year":"2024","journal-title":"Opto-Electron. Adv."},{"issue":"13","key":"2026091608072017800_cit14","doi-asserted-by":"publisher","DOI":"10.1126\/sciadv.abd7690","article-title":"Spectrally Encoded Single-Pixel Machine Vision\nUsing Diffractive Networks","volume":"7","author":"Li","year":"2021","journal-title":"Science Advances"},{"issue":"1","key":"2026091608072017800_cit15","doi-asserted-by":"publisher","first-page":"112","DOI":"10.1038\/s41377-019-0223-1","article-title":"Design of Task-Specific Optical Systems\nUsing Broadband Diffractive Neural Networks","volume":"8","author":"Luo","year":"2019","journal-title":"Light: Sci. Appl."},{"issue":"1","key":"2026091608072017800_cit16","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1038\/s41467-020-20327-5","article-title":"Terahertz Pulse Shaping\nUsing Diffractive Surfaces","volume":"12","author":"Veli","year":"2021","journal-title":"Nat. Commun."},{"issue":"1","key":"2026091608072017800_cit17","doi-asserted-by":"publisher","first-page":"6791","DOI":"10.1038\/s41467-023-42554-2","article-title":"Rapid Sensing of Hidden\nObjects and Defects Using a Single-Pixel Diffractive Terahertz Sensor","volume":"14","author":"Li","year":"2023","journal-title":"Nat. Commun."},{"issue":"10","key":"2026091608072017800_cit18","doi-asserted-by":"publisher","first-page":"2906","DOI":"10.1364\/OL.394046","article-title":"All-Optical\nDiffractive Neural Networked Terahertz Hologram","volume":"45","author":"Liao","year":"2020","journal-title":"Opt. Lett."},{"issue":"1","key":"2026091608072017800_cit19","doi-asserted-by":"publisher","first-page":"40","DOI":"10.1038\/s41377-021-00483-z","article-title":"Nanoprinted High-Neuron-Density Optical\nLinear Perceptrons Performing Near-Infrared Inference on a CMOS Chip","volume":"10","author":"Goi","year":"2021","journal-title":"Light Sci.  Appl."},{"issue":"10","key":"2026091608072017800_cit20","doi-asserted-by":"publisher","first-page":"1483","DOI":"10.1016\/j.eng.2020.07.032","article-title":"Diffractive Deep Neural Networks\nat Visible Wavelengths","volume":"7","author":"Chen","year":"2021","journal-title":"Engineering"},{"issue":"31","key":"2026091608072017800_cit21","doi-asserted-by":"publisher","DOI":"10.1002\/adma.202212091","article-title":"Data-Class-Specific All-Optical Transformations and Encryption","volume":"35","author":"Bai","year":"2023","journal-title":"Adv. Mater."},{"issue":"5","key":"2026091608072017800_cit22","doi-asserted-by":"publisher","first-page":"486","DOI":"10.1038\/s41566-025-01621-4","article-title":"All-optical image transportation\nthrough a multimode fibre using a miniaturized diffractive neural\nnetwork on the distal facet","volume":"19","author":"Yu","year":"2025","journal-title":"Nat. Photonics"},{"issue":"39","key":"2026091608072017800_cit23","doi-asserted-by":"publisher","DOI":"10.1002\/adfm.202214211","article-title":"Two-Photon Polymerization\nLithography for Optics and Photonics: Fundamentals, Materials, Technologies,\nand Applications","volume":"33","author":"Wang","year":"2023","journal-title":"Adv. Funct. Mater."},{"issue":"7","key":"2026091608072017800_cit24","doi-asserted-by":"publisher","DOI":"10.1002\/advs.202204072","article-title":"Two-Photon Polymerization:\nFundamentals, Materials, and Chemical Modification Strategies","volume":"10","author":"O\u2019Halloran","year":"2023","journal-title":"Advanced Science"},{"issue":"7","key":"2026091608072017800_cit25","doi-asserted-by":"publisher","DOI":"10.1002\/adom.202301938","article-title":"Classification of\nMetal Handwritten Digits Based on Microwave Diffractive Deep Neural\nNetwork","volume":"12","author":"Gu","year":"2024","journal-title":"Advanced Optical Materials"},{"issue":"1","key":"2026091608072017800_cit26","doi-asserted-by":"publisher","first-page":"7531","DOI":"10.1038\/s41467-022-35349-4","article-title":"Direct retrieval of Zernike-based\npupil functions using integrated diffractive deep neural networks","volume":"13","author":"Goi","year":"2022","journal-title":"Nat. Commun."},{"issue":"36","key":"2026091608072017800_cit27","doi-asserted-by":"publisher","first-page":"18597","DOI":"10.1039\/D5TC02037A","article-title":"Two-photon polymerization-assisted\n3D laser nanoprinting:\nfrom fundamentals to modern applications","volume":"13","author":"Boudene","year":"2025","journal-title":"Journal\nof Materials Chemistry C"},{"issue":"4","key":"2026091608072017800_cit28","doi-asserted-by":"publisher","DOI":"10.1088\/2631-7990\/ad35fe","article-title":"Two-photon polymerization\nlithography for imaging optics","volume":"6","author":"Wang","year":"2024","journal-title":"International\nJournal of Extreme Manufacturing"},{"issue":"8","key":"2026091608072017800_cit29","doi-asserted-by":"publisher","first-page":"10452","DOI":"10.1021\/acsnano.0c04313","article-title":"Toward Near-Perfect\nDiffractive Optical Elements via Nanoscale 3D Printing","volume":"14","author":"Wang","year":"2020","journal-title":"ACS Nano"},{"issue":"51","key":"2026091608072017800_cit30","doi-asserted-by":"publisher","DOI":"10.1126\/sciadv.adj9262","article-title":"3D-Printed Multilayer\nStructures for High-Numerical-Aperture Achromatic Metalenses","volume":"9","author":"Pan","year":"2023","journal-title":"Science Advances"},{"issue":"5","key":"2026091608072017800_cit31","doi-asserted-by":"publisher","DOI":"10.1002\/lpor.202501827","article-title":"Wide Angle 3D Imaging\nwithout Distortions","volume":"20","author":"Wu","year":"2026","journal-title":"Laser & Photonics Reviews"},{"issue":"13","key":"2026091608072017800_cit32","doi-asserted-by":"publisher","first-page":"4207","DOI":"10.1515\/nanoph-2020-0291","article-title":"Misalignment resilient\ndiffractive optical networks","volume":"9","author":"Mengu","year":"2018","journal-title":"Nanophotonics"},{"issue":"10","key":"2026091608072017800_cit33","doi-asserted-by":"publisher","DOI":"10.3788\/COL202422.102201","article-title":"Two-photon nanolithography\nof micrometer scale diffractive neural network with cubical diffraction\nneurons at the visible wavelength","volume":"22","author":"Wang","year":"2024","journal-title":"Chinese Optics\nLetters"},{"issue":"7894","key":"2026091608072017800_cit34","doi-asserted-by":"publisher","first-page":"549","DOI":"10.1038\/s41586-021-04223-6","article-title":"Deep\nphysical neural\nnetworks trained with backpropagation","volume":"601","author":"Wright","year":"2022","journal-title":"Nature"},{"issue":"7","key":"2026091608072017800_cit35","doi-asserted-by":"publisher","first-page":"803","DOI":"10.1364\/OPTICA.456108","article-title":"Hybrid training of optical neural networks","volume":"9","author":"Spall","year":"2022","journal-title":"Optica"},{"issue":"6643","key":"2026091608072017800_cit36","doi-asserted-by":"publisher","first-page":"398","DOI":"10.1126\/science.ade8450","article-title":"Experimentally realized in situ backpropagation\nfor deep learning in photonic neural networks","volume":"380","author":"Pai","year":"2023","journal-title":"Science"},{"issue":"1","key":"2026091608072017800_cit37","doi-asserted-by":"publisher","first-page":"7110","DOI":"10.1038\/s41467-023-42984-y","article-title":"Training large-scale\noptoelectronic neural networks with dual-neuron optical-artificial\nlearning","volume":"14","author":"Yuan","year":"2023","journal-title":"Nat. Commun."},{"issue":"14","key":"2026091608072017800_cit38","doi-asserted-by":"publisher","first-page":"20362","DOI":"10.1364\/OE.395986","article-title":"Thermal post-curing as an efficient\nstrategy to eliminate\nprocess parameter sensitivity in the mechanical properties of two-photon\npolymerized materials","volume":"28","author":"Bauer","year":"2020","journal-title":"Opt. Express"},{"issue":"10","key":"2026091608072017800_cit39","doi-asserted-by":"publisher","first-page":"7350","DOI":"10.1109\/TNNLS.2022.3141665","article-title":"Automatic sparse connectivity learning for\nneural networks","volume":"34","author":"Tang","year":"2023","journal-title":"IEEE Transactions on Neural\nNetworks and Learning Systems"}],"container-title":["Nano Letters"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/pubs.acs.org\/doi\/pdf\/10.1021\/acs.nanolett.6c01607","content-type":"application\/pdf","content-version":"vor","intended-application":"unspecified"},{"URL":"https:\/\/pubs.acs.org\/nalefd\/article-pdf\/26\/36\/11979\/67601565\/acs.nanolett.6c01607.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/pubs.acs.org\/nalefd\/article-pdf\/26\/36\/11979\/67601565\/acs.nanolett.6c01607.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T13:03:06Z","timestamp":1789563786000},"score":1,"resource":{"primary":{"URL":"https:\/\/pubs.acs.org\/nalefd\/article\/26\/36\/11979\/5348976\/Fabrication-Aware-Training-for-Two-Photon"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,28]]},"references-count":39,"journal-issue":{"issue":"36","published-online":{"date-parts":[[2026,8,28]]},"published-print":{"date-parts":[[2026,9,16]]}},"URL":"https:\/\/doi.org\/10.1021\/acs.nanolett.6c01607","relation":{},"ISSN":["1530-6984","1530-6992"],"issn-type":[{"value":"1530-6984","type":"print"},{"value":"1530-6992","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,28]]}}}