All-optical synthesis chip for large-scale intelligent semantic vision generation
Science · 18.12.2025 · 390 (6779) · 1259-1265
DOI: 10.1126/science.adv7434 ↗Kurz gefasst
Fachartikel in der Zeitschrift Science, erschienen am 18.12.2025. Verfasst von Yitong Chen und 6 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Image Communication and Network Engineering, Department of Electronic Engineering, School of Information Science and Electronic Engineer…. Die Arbeit wurde bisher 31-mal zitiert (Crossref) und nennt 68 Literaturangaben. Gefördert von: National key R&D program of China, Shanghai Science and Technology Program of Basic Research.
Abstract (Originalsprache)
Large-scale generative artificial intelligence (AI) is facing a severe computing power shortage. Although photonic computing achieves excellence in decision tasks, its application in generative tasks remains formidable because of limited integration scale, time-consuming dimension conversions, and ground-truth-dependent training algorithms. We produced an all-optical chip for large-scale intelligent vision generation, named LightGen. By integrating millions of photonic neurons on a chip, varying network dimension through proposed optical latent space, and Bayes-based training algorithms, LightGen experimentally implemented high-resolution semantic image generation, denoising, style transfer, three-dimensional generation, and manipulation. Its measured end-to-end computing speed and energy efficiency were each more than two orders of magnitude greater than those of state-of-the-art electronic chips, paving the way for acceleration of large visual generative models.
Autor:innen und Institutionen
- Institute of Image Communication and Network Engineering, Department of Electronic Engineering, School of Information Science and Electronic Engineering, Shanghai Jiao Tong University, Shanghai, China.
- Department of Automation, Tsinghua University, Beijing, China.
- Department of Electronic Engineering, Tsinghua University, Beijing, China.
ORCID-Profile: Yitong Chen, Xinyue Sun, Guangtao Zhai
Förderung
- National key R&D program of China
- Shanghai Science and Technology Program of Basic Research
Zitieren
APA
Chen, Y., Sun, X., Tan, L., Jiang, Y., Zhou, Y., Zhang, W., & Zhai, G. (2025). All-optical synthesis chip for large-scale intelligent semantic vision generation. Science, 390(6779), 1259-1265. https://doi.org/10.1126/science.adv7434
Vancouver
Chen Y, Sun X, Tan L, Jiang Y, Zhou Y, Zhang W, et al. All-optical synthesis chip for large-scale intelligent semantic vision generation. Science. 2025;390(6779):1259-1265. doi:10.1126/science.adv7434
BibTeX
@article{Chen2025,
author = {Chen, Yitong and Sun, Xinyue and Tan, Longtao and Jiang, Yizhou and Zhou, Yin and Zhang, Wenjun and Zhai, Guangtao},
title = {All-optical synthesis chip for large-scale intelligent semantic vision generation},
journal = {Science},
year = {2025},
volume = {390},
number = {6779},
pages = {1259--1265},
doi = {10.1126/science.adv7434}
}
EUVIMED