{"id":"https://openalex.org/W4415991950","doi":"https://doi.org/10.1109/infocom59046.2026.11571222","title":"Chameleon: Adaptive Fault Tolerance for Distributed Training via Real-time Policy Selection","display_name":"Chameleon: Adaptive Fault Tolerance for Distributed Training via Real-time Policy Selection","publication_year":2026,"publication_date":"2026-05-18","ids":{"openalex":"https://openalex.org/W4415991950","doi":"https://doi.org/10.1109/infocom59046.2026.11571222"},"language":"en","primary_location":{"id":"doi:10.1109/infocom59046.2026.11571222","is_oa":false,"landing_page_url":"https://doi.org/10.1109/infocom59046.2026.11571222","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE INFOCOM 2026 - IEEE Conference on Computer Communications","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2508.21613","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101924581","display_name":"Yuhang Zhou","orcid":"https://orcid.org/0009-0008-3067-3149"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhang Zhou","raw_affiliation_strings":["Nanjing University,State Key Laboratory for Novel Software Technology,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University,State Key Laboratory for Novel Software Technology,China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100332272","display_name":"Zhibin Wang","orcid":"https://orcid.org/0000-0001-7502-2181"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhibin Wang","raw_affiliation_strings":["Nanjing University,State Key Laboratory for Novel Software Technology,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University,State Key Laboratory for Novel Software Technology,China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025010135","display_name":"Peng Jiang","orcid":"https://orcid.org/0000-0002-7828-5486"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Jiang","raw_affiliation_strings":["Nanjing University,State Key Laboratory for Novel Software Technology,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University,State Key Laboratory for Novel Software Technology,China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021964629","display_name":"Haoran Xia","orcid":"https://orcid.org/0000-0002-4040-3061"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoran Xia","raw_affiliation_strings":["Nanjing University,State Key Laboratory for Novel Software Technology,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University,State Key Laboratory for Novel Software Technology,China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019335078","display_name":"Junhe Lu","orcid":"https://orcid.org/0000-0001-6068-5820"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junhe Lu","raw_affiliation_strings":["Nanjing University,State Key Laboratory for Novel Software Technology,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University,State Key Laboratory for Novel Software Technology,China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072192790","display_name":"Qianyu Jiang","orcid":"https://orcid.org/0000-0002-2877-0176"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qianyu Jiang","raw_affiliation_strings":["Nanjing University,State Key Laboratory for Novel Software Technology,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University,State Key Laboratory for Novel Software Technology,China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052175650","display_name":"Rong Gu","orcid":"https://orcid.org/0000-0002-1565-9997"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rong Gu","raw_affiliation_strings":["Nanjing University,State Key Laboratory for Novel Software Technology,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University,State Key Laboratory for Novel Software Technology,China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100409277","display_name":"Huimian Xu","orcid":"https://orcid.org/0000-0002-1177-4445"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hengxi Xu","raw_affiliation_strings":["Huawei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei,China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072068932","display_name":"Xinjing Huang","orcid":"https://orcid.org/0000-0002-8964-8502"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinjing Huang","raw_affiliation_strings":["Huawei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei,China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111911454","display_name":"Guo Hua Fang","orcid":null},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guanghuan Fang","raw_affiliation_strings":["Huawei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei,China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108824644","display_name":"Zhiheng Hu","orcid":"https://orcid.org/0009-0004-7821-070X"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiheng Hu","raw_affiliation_strings":["Huawei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei,China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100458628","display_name":"Jingyi Zhang","orcid":"https://orcid.org/0000-0002-8172-5104"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingyi Zhang","raw_affiliation_strings":["Huawei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei,China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yongjin Cai","orcid":null},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongjin Cai","raw_affiliation_strings":["Huawei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei,China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014610561","display_name":"Jianhua He","orcid":"https://orcid.org/0000-0002-5738-8507"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian He","raw_affiliation_strings":["Huawei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei,China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100751736","display_name":"Chen Tian","orcid":"https://orcid.org/0000-0003-2710-7628"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen Tian","raw_affiliation_strings":["Nanjing University,State Key Laboratory for Novel Software Technology,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University,State Key Laboratory for Novel Software Technology,China","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":0.31459999084472656,"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/T12127","display_name":"Software System Performance and Reliability","score":0.31459999084472656,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.08649999648332596,"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/T10772","display_name":"Distributed systems and fault tolerance","score":0.07519999891519547,"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/training","display_name":"Training (meteorology)","score":0.6171000003814697},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5799999833106995},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.536300003528595},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.5360000133514404},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4074000120162964},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.3824000060558319},{"id":"https://openalex.org/keywords/plan","display_name":"Plan (archaeology)","score":0.3700000047683716},{"id":"https://openalex.org/keywords/resilience","display_name":"Resilience (materials science)","score":0.3402999937534332}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7980999946594238},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.6171000003814697},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5799999833106995},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.536300003528595},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.5360000133514404},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4352000057697296},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41749998927116394},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4074000120162964},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3862999975681305},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.3824000060558319},{"id":"https://openalex.org/C2776505523","wikidata":"https://www.wikidata.org/wiki/Q4785468","display_name":"Plan (archaeology)","level":2,"score":0.3700000047683716},{"id":"https://openalex.org/C2779585090","wikidata":"https://www.wikidata.org/wiki/Q3457762","display_name":"Resilience (materials science)","level":2,"score":0.3402999937534332},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.3160000145435333},{"id":"https://openalex.org/C2777115002","wikidata":"https://www.wikidata.org/wiki/Q7168246","display_name":"Performance prediction","level":2,"score":0.30959999561309814},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.29339998960494995},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.28769999742507935},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.2856000065803528},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.262800008058548},{"id":"https://openalex.org/C52970973","wikidata":"https://www.wikidata.org/wiki/Q2497134","display_name":"Adaptive system","level":2,"score":0.25440001487731934},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.25429999828338623},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2535000145435333}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/infocom59046.2026.11571222","is_oa":false,"landing_page_url":"https://doi.org/10.1109/infocom59046.2026.11571222","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE INFOCOM 2026 - IEEE Conference on Computer Communications","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2508.21613","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.21613","pdf_url":"https://arxiv.org/pdf/2508.21613","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"pmh:oai:arXiv.org:2508.21613","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2508.21613","pdf_url":"https://arxiv.org/pdf/2508.21613","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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.2508.21613","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2508.21613","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2508.21613","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.21613","pdf_url":"https://arxiv.org/pdf/2508.21613","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":[],"awards":[{"id":"https://openalex.org/G3568657126","display_name":null,"funder_award_id":"BK20243053","funder_id":"https://openalex.org/F4320322769","funder_display_name":"Natural Science Foundation of Jiangsu Province"},{"id":"https://openalex.org/G575347255","display_name":null,"funder_award_id":"BK20243053","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7905192568","display_name":null,"funder_award_id":"62325205","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321605","display_name":"Government of Jiangsu Province","ror":"https://ror.org/004svx814"},{"id":"https://openalex.org/F4320322769","display_name":"Natural Science Foundation of Jiangsu Province","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320324852","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Training":[0],"large":[1],"language":[2],"models":[3],"faces":[4],"frequent":[5],"interruptions":[6],"due":[7],"to":[8,104,110],"various":[9],"faults,":[10],"demanding":[11],"robust":[12],"fault-tolerance.":[13],"Existing":[14],"backup-free":[15],"methods,":[16,106],"such":[17],"as":[18],"redundant":[19],"computation,":[20],"dynamic":[21],"parallelism,":[22],"and":[23,71,92,99,112,119],"data":[24],"rerouting,":[25],"each":[26],"incur":[27],"performance":[28,62,69,85],"penalties,":[29],"whether":[30],"from":[31],"ongoing":[32],"overhead,":[33],"lengthy":[34],"reconfigurations,":[35],"or":[36],"post-recovery":[37,91],"inefficiencies.":[38],"We":[39],"propose":[40],"Chameleon,":[41],"an":[42],"adaptive":[43],"fault-tolerant":[44],"system":[45],"that":[46,81],"intelligently":[47],"selects":[48],"optimal":[49],"recovery":[50],"strategies":[51],"when":[52],"a":[53,60,77,84],"failure":[54],"occurs.":[55],"Chameleon":[56,82,107],"achieves":[57,108],"this":[58],"through":[59],"unified":[61],"model,":[63],"expedient":[64],"execution":[65],"plan":[66],"search,":[67],"accurate":[68],"estimation,":[70],"efficient":[72,100],"communication":[73],"optimizations.":[74],"Experiments":[75],"on":[76],"32-card":[78],"cluster":[79],"show":[80],"maintains":[83],"gap":[86],"of":[87],"within":[88],"11.00%":[89],"between":[90],"failure-free":[93],"training,":[94],"while":[95],"preserving":[96],"model":[97],"convergence":[98],"memory":[101],"usage.":[102],"Compared":[103],"state-of-the-art":[105],"up":[109],"1.229x":[111],"1.355x":[113],"higher":[114],"average":[115],"throughput":[116],"than":[117],"Oobleck":[118],"Recycle,":[120],"respectively.":[121]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
