By embedding core computer vision principles into a large-scale optical metasurface, an efficient vision processing system using far fewer parameters is demonstrated to outperform many digital models and enables deployment on edge devices.
Shanahan, M., McDonell, K. & Reynolds, L. Role play with large language models. Nature623, 493498 (2023).
Article
ADS
CAS
PubMed
Google Scholar
Singhal, K. et al. Large… [+13698 chars]
Originally published by
Nature.com
