{"id":"https://openalex.org/W4416369015","doi":"https://doi.org/10.1177/10943420251394758","title":"Sequence length scaling in vision transformers for scientific images on frontier","display_name":"Sequence length scaling in vision transformers for scientific images on frontier","publication_year":2025,"publication_date":"2025-11-19","ids":{"openalex":"https://openalex.org/W4416369015","doi":"https://doi.org/10.1177/10943420251394758"},"language":"en","primary_location":{"id":"doi:10.1177/10943420251394758","is_oa":false,"landing_page_url":"https://doi.org/10.1177/10943420251394758","pdf_url":null,"source":{"id":"https://openalex.org/S60606485","display_name":"The International Journal of High Performance Computing Applications","issn_l":"1094-3420","issn":["1094-3420","1741-2846"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of High Performance Computing Applications","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5006493183","display_name":"Aristeidis Tsaris","orcid":"https://orcid.org/0000-0002-7734-3349"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Aristeidis Tsaris","raw_affiliation_strings":["National Center for Computational Sciences, Oak Ridge National Laboratory"],"raw_orcid":"https://orcid.org/0000-0002-7734-3349","affiliations":[{"raw_affiliation_string":"National Center for Computational Sciences, Oak Ridge National Laboratory","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100691056","display_name":"Chengming Zhang","orcid":"https://orcid.org/0000-0003-3008-9133"},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chengming Zhang","raw_affiliation_strings":["Indiana University Bloomington"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indiana University Bloomington","institution_ids":["https://openalex.org/I4210119109"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100411445","display_name":"Xiao Wang","orcid":"https://orcid.org/0000-0001-9781-6118"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiao Wang","raw_affiliation_strings":["Computational Sciences and Engineering Division, Oak Ridge National Laboratory, Oak Ridge, TN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Sciences and Engineering Division, Oak Ridge National Laboratory, Oak Ridge, TN, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051882926","display_name":"Junqi Yin","orcid":"https://orcid.org/0000-0003-3843-5520"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Junqi Yin","raw_affiliation_strings":["National Center for Computational Sciences, Oak Ridge National Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Center for Computational Sciences, Oak Ridge National Laboratory","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050820498","display_name":"Siyan Liu","orcid":"https://orcid.org/0000-0003-2017-3251"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Siyan Liu","raw_affiliation_strings":["Computational Sciences and Engineering Division, Oak Ridge National Laboratory, Oak Ridge, TN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Sciences and Engineering Division, Oak Ridge National Laboratory, Oak Ridge, TN, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012717451","display_name":"Moetasim Ashfaq","orcid":"https://orcid.org/0000-0003-4106-3027"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Moetasim Ashfaq","raw_affiliation_strings":["Computational Sciences and Engineering Division, Oak Ridge National Laboratory, Oak Ridge, TN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Sciences and Engineering Division, Oak Ridge National Laboratory, Oak Ridge, TN, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111771751","display_name":"Ming Fan","orcid":null},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ming Fan","raw_affiliation_strings":["Computational Sciences and Engineering Division, Oak Ridge National Laboratory, Oak Ridge, TN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Sciences and Engineering Division, Oak Ridge National Laboratory, Oak Ridge, TN, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054451484","display_name":"Jong Youl Choi","orcid":"https://orcid.org/0000-0002-6459-6152"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jong Youl Choi","raw_affiliation_strings":["Computer Science and Mathematics Division, Oak Ridge National Laboratory, Oak Ridge, TN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Mathematics Division, Oak Ridge National Laboratory, Oak Ridge, TN, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002208999","display_name":"Mohamed Wahib","orcid":"https://orcid.org/0000-0002-7165-2095"},"institutions":[{"id":"https://openalex.org/I4210129730","display_name":"RIKEN Center for Computational Science","ror":"https://ror.org/03r519674","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210129730"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Mohamed Wahib","raw_affiliation_strings":["High Performance Artificial Intelligence Systems, RIKEN Center for Computational Science"],"raw_orcid":"https://orcid.org/0000-0002-7165-2095","affiliations":[{"raw_affiliation_string":"High Performance Artificial Intelligence Systems, RIKEN Center for Computational Science","institution_ids":["https://openalex.org/I4210129730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112422192","display_name":"Dan Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dan Lu","raw_affiliation_strings":["Computational Sciences and Engineering Division, Oak Ridge National Laboratory, Oak Ridge, TN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Sciences and Engineering Division, Oak Ridge National Laboratory, Oak Ridge, TN, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068721920","display_name":"Prasanna Balaprakash","orcid":"https://orcid.org/0000-0002-0292-5715"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Prasanna Balaprakash","raw_affiliation_strings":["Computer Science and Mathematics Division, Oak Ridge National Laboratory, Oak Ridge, TN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Mathematics Division, Oak Ridge National Laboratory, Oak Ridge, TN, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101916963","display_name":"Feiyi Wang","orcid":"https://orcid.org/0000-0002-0099-1559"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Feiyi Wang","raw_affiliation_strings":["National Center for Computational Sciences, Oak Ridge National Laboratory"],"raw_orcid":"https://orcid.org/0000-0002-0099-1559","affiliations":[{"raw_affiliation_string":"National Center for Computational Sciences, Oak Ridge National Laboratory","institution_ids":["https://openalex.org/I1289243028"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":12,"corresponding_author_ids":["https://openalex.org/A5006493183"],"corresponding_institution_ids":["https://openalex.org/I1289243028"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.31321885,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"3","first_page":"273","last_page":"290"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.21459999680519104,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.21459999680519104,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T14347","display_name":"Big Data and Digital Economy","score":0.07329999655485153,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.05990000069141388,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6736000180244446},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5875999927520752},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.5189999938011169},{"id":"https://openalex.org/keywords/time-sequence","display_name":"Time sequence","score":0.37779998779296875},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.3610000014305115},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.34470000863075256},{"id":"https://openalex.org/keywords/data-parallelism","display_name":"Data parallelism","score":0.3384000062942505}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6829000115394592},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6736000180244446},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5875999927520752},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.5189999938011169},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.43220001459121704},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.414900004863739},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3928000032901764},{"id":"https://openalex.org/C3020136221","wikidata":"https://www.wikidata.org/wiki/Q186588","display_name":"Time sequence","level":2,"score":0.37779998779296875},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.3610000014305115},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.34470000863075256},{"id":"https://openalex.org/C61483411","wikidata":"https://www.wikidata.org/wiki/Q3124522","display_name":"Data parallelism","level":3,"score":0.3384000062942505},{"id":"https://openalex.org/C40506919","wikidata":"https://www.wikidata.org/wiki/Q7452469","display_name":"Sequence learning","level":2,"score":0.3165000081062317},{"id":"https://openalex.org/C2778571376","wikidata":"https://www.wikidata.org/wiki/Q1355821","display_name":"Frontier","level":2,"score":0.2971000075340271},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2782999873161316},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.273499995470047},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2720000147819519},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.25870001316070557},{"id":"https://openalex.org/C80469333","wikidata":"https://www.wikidata.org/wiki/Q189088","display_name":"Von Neumann architecture","level":2,"score":0.251800000667572},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.2513999938964844}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1177/10943420251394758","is_oa":false,"landing_page_url":"https://doi.org/10.1177/10943420251394758","pdf_url":null,"source":{"id":"https://openalex.org/S60606485","display_name":"The International Journal of High Performance Computing Applications","issn_l":"1094-3420","issn":["1094-3420","1741-2846"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of High Performance Computing Applications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8813984943","display_name":null,"funder_award_id":"DE-AC05-00OR22725","funder_id":"https://openalex.org/F4320316892","funder_display_name":"UT-Battelle"}],"funders":[{"id":"https://openalex.org/F4320316892","display_name":"UT-Battelle","ror":"https://ror.org/04nza6677"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2108598243","https://openalex.org/W3092103057","https://openalex.org/W3138516171","https://openalex.org/W3205803342","https://openalex.org/W4206706211","https://openalex.org/W4312468136","https://openalex.org/W4366742337","https://openalex.org/W4383218913","https://openalex.org/W4384820848","https://openalex.org/W4385571616","https://openalex.org/W4386768656","https://openalex.org/W4388697414","https://openalex.org/W4388728292","https://openalex.org/W4396816283","https://openalex.org/W4396982199","https://openalex.org/W4400410176","https://openalex.org/W4401018280","https://openalex.org/W4402263720"],"related_works":[],"abstract_inverted_index":{"Vision":[0],"Transformers":[1],"(ViTs)":[2],"are":[3],"pivotal":[4],"for":[5,26,37,47],"foundational":[6],"models":[7,93],"in":[8,33,73,89,92,128],"scientific":[9],"imagery,":[10],"including":[11],"Earth":[12],"science":[13],"applications,":[14],"due":[15],"to":[16,19,51,54,69,95,112,140],"their":[17],"capability":[18],"process":[20],"large":[21],"sequence":[22,31,45,71,87,144],"lengths.":[23],"While":[24],"transformers":[25],"text":[27],"have":[28],"inspired":[29],"scaling":[30,80],"lengths":[32],"ViTs,":[34,48,90],"adapting":[35],"these":[36,103],"ViTs":[38],"introduces":[39],"unique":[40],"challenges.":[41],"We":[42,101],"develop":[43],"distributed":[44],"parallelism":[46,72,88],"enabling":[49],"them":[50],"handle":[52],"up":[53,94],"1M":[55],"tokens.":[56],"Our":[57,119],"approach,":[58],"leveraging":[59],"DeepSpeed-Ulysses":[60],"and":[61,108],"Long-Sequence-Segmentation":[62],"with":[63,104,142],"model":[64,139],"sharding,":[65],"is":[66],"the":[67,132],"first":[68,133],"apply":[70],"ViT":[74],"training,":[75],"achieving":[76],"a":[77,136,143],"94%":[78],"batch":[79],"efficiency":[81],"on":[82],"2,048":[83],"AMD-MI250X":[84],"GPUs.":[85],"Evaluating":[86],"particularly":[91],"10B":[96],"parameters,":[97],"highlighted":[98],"substantial":[99],"bottlenecks.":[100],"countered":[102],"hybrid":[105],"sequence,":[106],"pipeline,":[107],"flash":[109],"attention":[110],"strategies,":[111],"scale":[113],"beyond":[114],"single":[115],"GPU":[116],"memory":[117],"limits.":[118],"method":[120],"significantly":[121],"enhances":[122],"climate":[123],"modeling":[124],"accuracy":[125],"by":[126],"20%":[127],"temperature":[129],"predictions,":[130],"marking":[131],"training":[134],"of":[135,146],"vision":[137],"transformer":[138],"convergence":[141],"length":[145],"188K":[147],"tokens,":[148],"using":[149],"full":[150],"self-attention.":[151]},"counts_by_year":[],"updated_date":"2026-06-05T09:01:59.212387","created_date":"2025-11-19T00:00:00"}
