Voltage-controlled magnetoelectric devices for neuromorphic diffusion process
Yang Cheng (),
Qingyuan Shu,
Albert Lee,
Haoran He,
Ivy Zhu,
Minzhang Chen,
Renhe Chen,
Zirui Wang,
Hantao Zhang,
Chih-Yao Wang,
Shan-Yi Yang,
Yu-Chen Hsin,
Cheng-Yi Shih,
Hsin-Han Lee,
Ran Cheng and
Kang L. Wang ()
Additional contact information
Yang Cheng: University of California
Qingyuan Shu: University of California
Albert Lee: University of California
Haoran He: University of California
Ivy Zhu: The Ohio State University
Minzhang Chen: University of California
Renhe Chen: University of California
Zirui Wang: University of California
Hantao Zhang: University of California
Chih-Yao Wang: Industrial Technology Research Institute
Shan-Yi Yang: Industrial Technology Research Institute
Yu-Chen Hsin: Industrial Technology Research Institute
Cheng-Yi Shih: Industrial Technology Research Institute
Hsin-Han Lee: Industrial Technology Research Institute
Ran Cheng: University of California
Kang L. Wang: University of California
Nature Communications, 2025, vol. 16, issue 1, 1-8
Abstract:
Abstract Neuromorphic diffusion models have become one of the major breakthroughs in the field of generative artificial intelligence. Unlike discriminative models that have been well developed to tackle classification or regression tasks, diffusion models aim at creating content based upon contexts learned. However, the more complex algorithms of these models result in high computational costs using today’s technologies. Here, we develop a spintronic voltage-controlled magnetoelectric memory hardware for the neuromorphic diffusion process. The in-memory computing capability of our spintronic devices goes beyond current Von Neumann architecture, where memory and computing units are separated. Together with the non-volatility of magnetic memory, we can achieve high-speed and low-cost computing, which is desirable for the increasing scale of generative models in the current era. We experimentally demonstrate that the hardware-based true random diffusion process can be implemented for image generation and achieve comparable image quality to software-based training as measured by the Fréchet inception distance (FID) score, achieving ~103 better energy-per-bit-per-area over traditional hardware.
Date: 2025
References: Add references at CitEc
Citations:
Downloads: (external link)
https://www.nature.com/articles/s41467-025-58932-x Abstract (text/html)
Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.
Export reference: BibTeX
RIS (EndNote, ProCite, RefMan)
HTML/Text
Persistent link: https://EconPapers.repec.org/RePEc:nat:natcom:v:16:y:2025:i:1:d:10.1038_s41467-025-58932-x
Ordering information: This journal article can be ordered from
https://www.nature.com/ncomms/
DOI: 10.1038/s41467-025-58932-x
Access Statistics for this article
Nature Communications is currently edited by Nathalie Le Bot, Enda Bergin and Fiona Gillespie
More articles in Nature Communications from Nature
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().