{"id":"https://openalex.org/W6903367718","doi":"https://doi.org/10.1145/3735358.3735372","title":"Mnemosyne: Lightweight and Fast Error Recovery for LLM Training in a Just-In-Time Manner","display_name":"Mnemosyne: Lightweight and Fast Error Recovery for LLM Training in a Just-In-Time Manner","publication_year":2025,"publication_date":"2025-07-17","ids":{"openalex":"https://openalex.org/W6903367718","doi":"https://doi.org/10.1145/3735358.3735372"},"language":"en","primary_location":{"id":"doi:10.1145/3735358.3735372","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3735358.3735372","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 9th Asia-Pacific Workshop on Networking","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3735358.3735372","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Jinyi Xia","orcid":"https://orcid.org/0009-0002-5975-5718"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinyi Xia","raw_affiliation_strings":["Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0002-5975-5718","affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Menghao Zhang","orcid":"https://orcid.org/0000-0001-5274-5512"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Menghao Zhang","raw_affiliation_strings":["Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-5274-5512","affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jiaxun Huang","orcid":"https://orcid.org/0009-0009-8999-6468"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaxun Huang","raw_affiliation_strings":["Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0009-8999-6468","affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yuezheng Liu","orcid":"https://orcid.org/0009-0001-5443-2066"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuezheng Liu","raw_affiliation_strings":["Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0001-5443-2066","affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xiaohe Hu","orcid":"https://orcid.org/0000-0003-1487-2419"},"institutions":[{"id":"https://openalex.org/I1324360087","display_name":"Infinera (United States)","ror":"https://ror.org/02ty5cy83","country_code":"US","type":"company","lineage":["https://openalex.org/I1324360087"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaohe Hu","raw_affiliation_strings":["Infrawaves, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-1487-2419","affiliations":[{"raw_affiliation_string":"Infrawaves, Beijing, China","institution_ids":["https://openalex.org/I1324360087"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xudong Liu","orcid":"https://orcid.org/0009-0007-8865-3055"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xudong Liu","raw_affiliation_strings":["Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0007-8865-3055","affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"last","author":{"id":null,"display_name":"Chunming Hu","orcid":"https://orcid.org/0000-0003-3473-9703"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunming Hu","raw_affiliation_strings":["Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-3473-9703","affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"157","last_page":"163"},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10916","display_name":"Surgical Simulation and Training","score":0.13109999895095825,"subfield":{"id":"https://openalex.org/subfields/2746","display_name":"Surgery"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T10916","display_name":"Surgical Simulation and Training","score":0.13109999895095825,"subfield":{"id":"https://openalex.org/subfields/2746","display_name":"Surgery"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11238","display_name":"Simulation-Based Education in Healthcare","score":0.04580000042915344,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.01940000057220459,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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":0.5060999989509583},{"id":"https://openalex.org/keywords/troubleshooting","display_name":"Troubleshooting","score":0.32179999351501465},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.28360000252723694},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.28029999136924744}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5429999828338623},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5060999989509583},{"id":"https://openalex.org/C147494362","wikidata":"https://www.wikidata.org/wiki/Q2078905","display_name":"Troubleshooting","level":2,"score":0.32179999351501465},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.30059999227523804},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2937000095844269},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.28360000252723694},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.28029999136924744},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.25760000944137573},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.24869999289512634},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.2475000023841858}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3735358.3735372","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3735358.3735372","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 9th Asia-Pacific Workshop on Networking","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3735358.3735372","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3735358.3735372","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 9th Asia-Pacific Workshop on Networking","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W3021124033","https://openalex.org/W3072623287","https://openalex.org/W3091097978","https://openalex.org/W3193985311","https://openalex.org/W4386840193","https://openalex.org/W4387302750","https://openalex.org/W4394923484","https://openalex.org/W4398796293","https://openalex.org/W4400682050","https://openalex.org/W4401176822","https://openalex.org/W4405756264"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}