{"id":"https://openalex.org/W7129028000","doi":"https://doi.org/10.48550/arxiv.2602.12529","title":"Flow-Factory: A Unified Framework for Reinforcement Learning in Flow-Matching Models","display_name":"Flow-Factory: A Unified Framework for Reinforcement Learning in Flow-Matching Models","publication_year":2026,"publication_date":"2026-02-13","ids":{"openalex":"https://openalex.org/W7129028000","doi":"https://doi.org/10.48550/arxiv.2602.12529"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2602.12529","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2602.12529","pdf_url":"https://arxiv.org/pdf/2602.12529","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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/2602.12529","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5099137302","display_name":"Bowen Ping","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]},{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ping, Bowen","raw_affiliation_strings":["Jiaotong University CFAR ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jiaotong University CFAR ,","institution_ids":["https://openalex.org/I21193070","https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062654071","display_name":"Chengyou Jia","orcid":"https://orcid.org/0000-0001-6921-0303","observed_orcids":["https://orcid.org/0000-0001-6921-0303"]},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]},{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jia, Chengyou","raw_affiliation_strings":["Jiaotong University CFAR ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jiaotong University CFAR ,","institution_ids":["https://openalex.org/I21193070","https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138388669","display_name":"Minnan Luo","orcid":"https://orcid.org/0000-0002-0140-7860","observed_orcids":["https://orcid.org/0000-0002-0140-7860"]},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]},{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Luo, Minnan","raw_affiliation_strings":["Jiaotong University CFAR ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jiaotong University CFAR ,","institution_ids":["https://openalex.org/I21193070","https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052221167","display_name":"Hangwei Qian","orcid":"https://orcid.org/0000-0003-4831-0748","observed_orcids":["https://orcid.org/0000-0003-4831-0748"]},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]},{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qian, Hangwei","raw_affiliation_strings":["Jiaotong University CFAR ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jiaotong University CFAR ,","institution_ids":["https://openalex.org/I21193070","https://openalex.org/I87445476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021751767","display_name":"Ivor Wai-Hung Tsang","orcid":"https://orcid.org/0000-0001-8095-4637","observed_orcids":["https://orcid.org/0000-0001-8095-4637","https://orcid.org/0000-0003-2211-8176"]},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]},{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tsang, Ivor","raw_affiliation_strings":["Jiaotong University CFAR ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jiaotong University CFAR ,","institution_ids":["https://openalex.org/I21193070","https://openalex.org/I87445476"]}]}],"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9965999722480774,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9965999722480774,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.0010000000474974513,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.0003000000142492354,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/diffusion-models","display_name":"diffusion models","score":0.7300000190734863},{"id":"https://openalex.org/keywords/preference-alignment","display_name":"preference alignment","score":0.531000018119812},{"id":"https://openalex.org/keywords/modular-framework","display_name":"modular framework","score":0.5090000033378601},{"id":"https://openalex.org/keywords/memory-optimization","display_name":"memory optimization","score":0.9070000052452087},{"id":"https://openalex.org/keywords/distributed-training","display_name":"distributed training","score":0.9829999804496765},{"id":"https://openalex.org/keywords/flux","display_name":"flux","score":0.44200000166893005}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7445999979972839},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7422000169754028},{"id":"https://openalex.org/C51929080","wikidata":"https://www.wikidata.org/wiki/Q2425187","display_name":"Codebase","level":3,"score":0.5659999847412109},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.44830000400543213},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44020000100135803},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.41119998693466187},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4106000065803528},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.26460000872612},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.25949999690055847},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25929999351501465},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.2558000087738037}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2602.12529","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2602.12529","pdf_url":"https://arxiv.org/pdf/2602.12529","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2602.12529","doi":"https://doi.org/10.48550/arxiv.2602.12529","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.12529","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2602.12529","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2602.12529","pdf_url":"https://arxiv.org/pdf/2602.12529","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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/W7129028000.pdf","grobid_xml":"https://content.openalex.org/works/W7129028000.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7147102754","https://openalex.org/W7220686408","https://openalex.org/W7162404255","https://openalex.org/W7077063683","https://openalex.org/W4416369166","https://openalex.org/W7117163874","https://openalex.org/W7168512064","https://openalex.org/W7164143790","https://openalex.org/W4413146459","https://openalex.org/W4415797121"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1],"has":[2],"emerged":[3],"as":[4,55],"a":[5,30,41],"promising":[6],"paradigm":[7],"for":[8,60],"aligning":[9],"diffusion":[10],"and":[11,24,37,53,63,68,82,96],"flow-matching":[12],"models":[13],"with":[14,86],"human":[15],"preferences,":[16],"yet":[17],"practitioners":[18],"face":[19],"fragmented":[20],"codebases,":[21],"model-specific":[22],"implementations,":[23],"engineering":[25],"complexity.":[26],"We":[27],"introduce":[28],"Flow-Factory,":[29],"unified":[31],"framework":[32],"that":[33],"decouples":[34],"algorithms,":[35],"models,":[36],"rewards":[38],"through":[39,40],"modular,":[42],"registry-based":[43],"architecture.":[44],"This":[45],"design":[46],"enables":[47],"seamless":[48,97],"integration":[49],"of":[50],"new":[51],"algorithms":[52],"architectures,":[54],"demonstrated":[56],"by":[57],"our":[58],"support":[59],"GRPO,":[61],"DiffusionNFT,":[62],"AWM":[64],"across":[65],"Flux,":[66],"Qwen-Image,":[67],"WAN":[69],"video":[70],"models.":[71],"By":[72],"minimizing":[73],"implementation":[74],"overhead,":[75],"Flow-Factory":[76,88],"empowers":[77],"researchers":[78],"to":[79],"rapidly":[80],"prototype":[81],"scale":[83],"future":[84],"innovations":[85],"ease.":[87],"provides":[89],"production-ready":[90],"memory":[91],"optimization,":[92],"flexible":[93],"multi-reward":[94],"training,":[95],"distributed":[98],"training":[99],"support.":[100],"The":[101],"codebase":[102],"is":[103],"available":[104],"at":[105],"https://github.com/X-GenGroup/Flow-Factory.":[106]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-02-17T00:00:00"}