{"id":"https://openalex.org/W7204791071","doi":"https://doi.org/10.48550/arxiv.2608.27865","title":"FFSlim: An Efficient and Lightweight Format for Multi-modal Data Storage and Retrieval","display_name":"FFSlim: An Efficient and Lightweight Format for Multi-modal Data Storage and Retrieval","publication_year":2026,"publication_date":"2026-08-28","ids":{"openalex":"https://openalex.org/W7204791071","doi":"https://doi.org/10.48550/arxiv.2608.27865"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.27865","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.27865","pdf_url":"https://arxiv.org/pdf/2608.27865","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.27865","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5148771766","display_name":"Long Yang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Long","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148790124","display_name":"Yu Mao","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mao, Yu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148781899","display_name":"Yuchen Shao","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shao, Yuchen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113172041","display_name":"Yumiao Zhao","orcid":"https://orcid.org/0000-0001-7803-2887","observed_orcids":["https://orcid.org/0000-0001-7803-2887"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Yumiao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100693160","display_name":"Yaqi Li","orcid":"https://orcid.org/0009-0005-5914-2999","observed_orcids":["https://orcid.org/0009-0005-5914-2999","https://orcid.org/0009-0007-6040-2609","https://orcid.org/0009-0007-8785-4998","https://orcid.org/0000-0003-4431-5103"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Yaqi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148824039","display_name":"Xuan Liu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Xuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148823633","display_name":"Xiaolong Shen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shen, Xiaolong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148798360","display_name":"Tao Yu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Tao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5159115104","display_name":"Gezi Li","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Gezi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148786439","display_name":"Jing Wang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Jing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113283222","display_name":"Chengcheng Wan","orcid":"https://orcid.org/0000-0001-9162-9688","observed_orcids":["https://orcid.org/0000-0001-9162-9688","https://orcid.org/0000-0003-4559-5426"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wan, Chengcheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5148789213","display_name":"Liang Shi","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shi, Liang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9746000170707703,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9746000170707703,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.009800000116229057,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.006300000008195639,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/storage-redundancy","display_name":"storage redundancy","score":0.49300000071525574},{"id":"https://openalex.org/keywords/adaptive-retrieval","display_name":"adaptive retrieval","score":0.6480000019073486},{"id":"https://openalex.org/keywords/redundancy-detection","display_name":"redundancy detection","score":0.5270000100135803},{"id":"https://openalex.org/keywords/i-o-bottleneck","display_name":"I/O bottleneck","score":0.6909999847412109},{"id":"https://openalex.org/keywords/training-efficiency","display_name":"training efficiency","score":0.6230000257492065}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8482999801635742},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.7572000026702881},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.7239000201225281},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.6557999849319458},{"id":"https://openalex.org/C7545210","wikidata":"https://www.wikidata.org/wiki/Q838123","display_name":"Data redundancy","level":2,"score":0.5551999807357788},{"id":"https://openalex.org/C194739806","wikidata":"https://www.wikidata.org/wiki/Q66221","display_name":"Computer data storage","level":2,"score":0.5300999879837036},{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.44350001215934753},{"id":"https://openalex.org/C551230270","wikidata":"https://www.wikidata.org/wiki/Q4368942","display_name":"Data retrieval","level":2,"score":0.414000004529953},{"id":"https://openalex.org/C83489325","wikidata":"https://www.wikidata.org/wiki/Q1332256","display_name":"Data striping","level":2,"score":0.3862000107765198},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.384799987077713},{"id":"https://openalex.org/C2779659223","wikidata":"https://www.wikidata.org/wiki/Q7619926","display_name":"Storage model","level":2,"score":0.38370001316070557},{"id":"https://openalex.org/C47487241","wikidata":"https://www.wikidata.org/wiki/Q5227230","display_name":"Data access","level":2,"score":0.3776000142097473},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3698999881744385},{"id":"https://openalex.org/C2780940931","wikidata":"https://www.wikidata.org/wiki/Q174989","display_name":"File system","level":2,"score":0.3569999933242798},{"id":"https://openalex.org/C97250363","wikidata":"https://www.wikidata.org/wiki/Q235557","display_name":"File format","level":2,"score":0.3370000123977661},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.32420000433921814},{"id":"https://openalex.org/C19012869","wikidata":"https://www.wikidata.org/wiki/Q578372","display_name":"Response time","level":2,"score":0.32359999418258667},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.3100999891757965},{"id":"https://openalex.org/C59276292","wikidata":"https://www.wikidata.org/wiki/Q580427","display_name":"Database index","level":3,"score":0.30709999799728394},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.3046000003814697},{"id":"https://openalex.org/C2985529240","wikidata":"https://www.wikidata.org/wiki/Q193395","display_name":"Digital storage","level":2,"score":0.2935999929904938},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.29280000925064087},{"id":"https://openalex.org/C2985331491","wikidata":"https://www.wikidata.org/wiki/Q5227298","display_name":"Data format","level":2,"score":0.27790001034736633},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.27630001306533813},{"id":"https://openalex.org/C137627569","wikidata":"https://www.wikidata.org/wiki/Q245471","display_name":"Cyclic redundancy check","level":3,"score":0.27000001072883606},{"id":"https://openalex.org/C24885549","wikidata":"https://www.wikidata.org/wiki/Q339678","display_name":"Distributed data store","level":2,"score":0.26109999418258667},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2556000053882599}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.27865","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.27865","pdf_url":"https://arxiv.org/pdf/2608.27865","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.27865","doi":"https://doi.org/10.48550/arxiv.2608.27865","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.27865","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.27865","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.27865","pdf_url":"https://arxiv.org/pdf/2608.27865","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204791071.pdf","grobid_xml":"https://content.openalex.org/works/W7204791071.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7122645051","https://openalex.org/W4394906083","https://openalex.org/W7162399423","https://openalex.org/W2414383802","https://openalex.org/W4401906965","https://openalex.org/W2760390332","https://openalex.org/W4406316555","https://openalex.org/W7204176632","https://openalex.org/W7161597045","https://openalex.org/W7117462385"],"abstract_inverted_index":{"With":[0],"the":[1,59,126,148],"rapid":[2],"expansion":[3],"of":[4],"large-scale":[5],"media-text":[6],"corpora,":[7],"multi-modal":[8,34,76,174],"datasets":[9,124],"increasingly":[10],"require":[11],"efficient":[12],"storage":[13,37,52,80,153],"and":[14,22,44,53,56,74,82,96,109,114,118,137,142,154],"retrieval.":[15],"Existing":[16],"formats":[17],"such":[18],"as":[19],"Files,":[20],"TDP,":[21],"FFRecord":[23],"work":[24],"adequately":[25],"for":[26,72],"uni-modal":[27],"data":[28,140],"but":[29],"expose":[30],"fundamental":[31],"limitations":[32],"in":[33,62],"settings,":[35],"including":[36],"redundancy,":[38],"massive":[39],"small-file":[40,98],"overheads,":[41],"cache-unfriendly":[42],"layouts,":[43],"heavy":[45],"index":[46,155],"structures.":[47],"These":[48],"issues":[49],"jointly":[50],"inflate":[51],"memory":[54],"usage":[55],"make":[57],"I/O":[58,160],"dominant":[60],"bottleneck":[61],"real":[63],"training":[64,167],"workloads.":[65],"We":[66],"present":[67],"FFSlim,":[68],"a":[69,88,115],"lightweight":[70],"format":[71,91],"storing":[73],"retrieving":[75],"data.":[77],"FFSlim":[78,127,134,163],"improves":[79],"efficiency":[81],"loading":[83,141],"throughput":[84,144],"through":[85],"three":[86],"components:":[87],"unified":[89],"file":[90],"that":[92,104,121,133],"removes":[93],"media":[94,112],"duplication":[95],"avoids":[97],"proliferation;":[99],"an":[100],"adaptive":[101],"retrieval":[102],"mechanism":[103],"enables":[105],"low-overhead":[106],"pair-level":[107],"access":[108],"accelerates":[110],"repeated":[111],"loading;":[113],"redundancy":[116],"detection":[117],"aggregation":[119],"module":[120],"converts":[122],"existing":[123],"into":[125],"layout.":[128],"The":[129],"experimental":[130],"results":[131],"demonstrate":[132],"achieves":[135],"2.07x":[136],"8.26x":[138],"higher":[139],"write":[143],"on":[145],"average":[146],"than":[147],"strongest":[149],"baseline,":[150],"with":[151],"minimal":[152],"overhead.":[156],"Consequently,":[157],"these":[158],"underlying":[159],"accelerations":[161],"enable":[162],"to":[164],"reduce":[165],"end-to-end":[166],"time":[168],"by":[169],"5.36%-14.18%":[170],"across":[171],"seven":[172],"diverse":[173],"models.":[175]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-09-01T00:00:00"}