Approximating vision transformers for edge: variational inference and mixed-precision for multi-modal data

dc.contributor.author	Katare, Dewant
dc.contributor.author	Leroux, Sam
dc.contributor.author	Janssen, Marijn
dc.contributor.author	Ding, Aaron Yi
dc.contributor.imecauthor	Leroux, Sam
dc.contributor.orcidimec	Leroux, Sam::0000-0003-3792-5026
dc.date.accessioned	2025-02-20T08:42:28Z
dc.date.available	2025-02-19T21:37:37Z
dc.date.available	2025-02-20T08:42:28Z
dc.date.issued	2025
dc.description.wosFundingText	This work was supported by the European Union's Horizon 2020 Research and Innovation Programme, under the Marie Sk & lstrok;odowska Curie grant agreement No. 956090 (APROPOS), and from the Flemish Government under the "Onderzoeksprogramma Artificiele Intelligentie (AI) Vlaanderen" programme.
dc.identifier.doi	10.1007/s00607-025-01427-w
dc.identifier.issn	0010-485X
dc.identifier.uri	https://imec-publications.be/handle/20.500.12860/45236
dc.publisher	SPRINGER WIEN
dc.source.beginpage	1
dc.source.endpage	25
dc.source.issue	3
dc.source.journal	COMPUTING
dc.source.numberofpages	25
dc.source.volume	107
dc.title	Approximating vision transformers for edge: variational inference and mixed-precision for multi-modal data
dc.type	Journal article
dspace.entity.type	Publication
Files	Original bundle Name: 8756.pdf Size: 2.62 MB Format: Adobe Portable Document Format Description: Download
Publication available in collections:	Articles