LOST-ViT: a low overhead soft error tolerance framework for vision transformers via model compression and selective bit-level redundancy
Journal of Systems Architecture · 2026-01 · 170 · 103623
DOI: 10.1016/j.sysarc.2025.103623 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Systems Architecture, 2026-01. Verfasst von Setareh Ahsaei und 1 weiteren Autor:innen. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 61 Literaturangaben.
Abstract (Originalsprache)
Kein Abstract verfügbar.
Zitieren
APA
Ahsaei, S., & Raji, M. (2026). LOST-ViT: a low overhead soft error tolerance framework for vision transformers via model compression and selective bit-level redundancy. Journal of Systems Architecture, 170, 103623. https://doi.org/10.1016/j.sysarc.2025.103623
Vancouver
Ahsaei S, Raji M. LOST-ViT: a low overhead soft error tolerance framework for vision transformers via model compression and selective bit-level redundancy. Journal of Systems Architecture. 2026;170:103623. doi:10.1016/j.sysarc.2025.103623
BibTeX
@article{Ahsaei2026,
author = {Ahsaei, Setareh and Raji, Mohsen},
title = {LOST-ViT: a low overhead soft error tolerance framework for vision transformers via model compression and selective bit-level redundancy},
journal = {Journal of Systems Architecture},
year = {2026},
volume = {170},
pages = {103623},
doi = {10.1016/j.sysarc.2025.103623}
}
EUVIMED