{"id":"https://openalex.org/W7220967289","doi":"https://doi.org/10.48550/arxiv.2610.08717","title":"Co-Evolving Paths and Flows via Path-Flow Alignment","display_name":"Co-Evolving Paths and Flows via Path-Flow Alignment","publication_year":2026,"publication_date":"2026-10-06","ids":{"openalex":"https://openalex.org/W7220967289","doi":"https://doi.org/10.48550/arxiv.2610.08717"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.08717","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.08717","pdf_url":"https://arxiv.org/pdf/2610.08717","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/2610.08717","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114626242","display_name":"Zeyu Michael Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Li, Zeyu Michael","raw_affiliation_strings":["Duke University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Duke University","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5152884126","display_name":"William Xingxu Chen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chen, William Xingxu","raw_affiliation_strings":["Duke University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Duke University","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5157904728","display_name":"Xiang Cheng","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cheng, Xiang","raw_affiliation_strings":["Duke University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Duke University","institution_ids":["https://openalex.org/I170897317"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I170897317"],"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":0.9970999956130981,"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":0.9970999956130981,"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/T11206","display_name":"Model Reduction and Neural Networks","score":0.0003000000142492354,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.00019999999494757503,"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/flow-matching","display_name":"flow matching","score":0.9909999966621399},{"id":"https://openalex.org/keywords/path-interpolation","display_name":"path interpolation","score":0.4690000116825104},{"id":"https://openalex.org/keywords/image-generation","display_name":"image generation","score":0.35100001096725464},{"id":"https://openalex.org/keywords/image-to-image-translation","display_name":"image-to-image translation","score":0.453000009059906}],"concepts":[{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.6604999899864197},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6043999791145325},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5752000212669373},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.48159998655319214},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.43209999799728394},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.42250001430511475},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.3894999921321869},{"id":"https://openalex.org/C38349280","wikidata":"https://www.wikidata.org/wiki/Q1434290","display_name":"Flow (mathematics)","level":2,"score":0.37380000948905945},{"id":"https://openalex.org/C32638748","wikidata":"https://www.wikidata.org/wiki/Q5437051","display_name":"Fast path","level":4,"score":0.3637999892234802},{"id":"https://openalex.org/C158485040","wikidata":"https://www.wikidata.org/wiki/Q4778119","display_name":"Any-angle path planning","level":4,"score":0.3635999858379364},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.33820000290870667},{"id":"https://openalex.org/C167981619","wikidata":"https://www.wikidata.org/wiki/Q1685498","display_name":"Cross entropy","level":3,"score":0.33160001039505005},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.33079999685287476},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.31859999895095825},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.31369999051094055},{"id":"https://openalex.org/C60008888","wikidata":"https://www.wikidata.org/wiki/Q6031013","display_name":"Information bottleneck method","level":3,"score":0.30480000376701355},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.29350000619888306},{"id":"https://openalex.org/C129045301","wikidata":"https://www.wikidata.org/wiki/Q7144654","display_name":"Path length","level":2,"score":0.2928999960422516},{"id":"https://openalex.org/C114809511","wikidata":"https://www.wikidata.org/wiki/Q1412924","display_name":"Flow network","level":2,"score":0.2865000069141388},{"id":"https://openalex.org/C137800194","wikidata":"https://www.wikidata.org/wiki/Q11713455","display_name":"Interpolation (computer graphics)","level":3,"score":0.28540000319480896},{"id":"https://openalex.org/C1465435","wikidata":"https://www.wikidata.org/wiki/Q2916352","display_name":"Longest path problem","level":4,"score":0.2847999930381775},{"id":"https://openalex.org/C8272713","wikidata":"https://www.wikidata.org/wiki/Q176737","display_name":"Stochastic process","level":2,"score":0.2736000120639801},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26989999413490295},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.26809999346733093},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.2614000141620636}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.08717","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.08717","pdf_url":"https://arxiv.org/pdf/2610.08717","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.2610.08717","doi":"https://doi.org/10.48550/arxiv.2610.08717","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.08717","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:2610.08717","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.08717","pdf_url":"https://arxiv.org/pdf/2610.08717","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/W7220967289.pdf","grobid_xml":"https://content.openalex.org/works/W7220967289.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7128717722","https://openalex.org/W7204101447","https://openalex.org/W7215900325","https://openalex.org/W7160115508","https://openalex.org/W7151252295","https://openalex.org/W7136577520","https://openalex.org/W7160597965","https://openalex.org/W7128367715","https://openalex.org/W7221754878","https://openalex.org/W7163085662"],"abstract_inverted_index":{"We":[0,82,99],"study":[1],"path-flow":[2,174],"alignment":[3,38,71,92],"as":[4],"a":[5,32,66,76,86,131],"unified":[6],"training":[7,175],"objective":[8],"for":[9,79,158],"flow":[10,33,41],"matching.":[11],"Instead":[12],"of":[13,138],"fixing":[14],"the":[15,21,36,40,45,49,57,70,91,110,115,139,143,159,166,169,196],"interpolation":[16],"path":[17,29,46,50,64,80,84,117,133,144],"and":[18,31,48,163,194,199],"learning":[19],"only":[20],"velocity":[22,55],"field,":[23],"we":[24,129],"jointly":[25],"train":[26],"an":[27,154],"endpoint-preserving":[28],"network":[30,34,145],"using":[35],"same":[37],"loss:":[39],"learns":[42,51],"to":[43,52,56,191],"match":[44],"velocity,":[47],"align":[53],"its":[54],"current":[58],"flow.":[59],"Although":[60],"every":[61],"fixed":[62],"learned":[63,116,170],"defines":[65],"valid":[67],"flow-matching":[68],"objective,":[69],"loss":[72,93],"alone":[73],"is":[74,104,203],"not":[75],"reliable":[77],"criterion":[78],"learning.":[81],"identify":[83],"overfitting,":[85],"failure":[87,103],"mode":[88],"in":[89,109,168],"which":[90],"decreases":[94],"while":[95,146],"sample":[96],"quality":[97],"worsens.":[98],"find":[100],"that":[101,135],"this":[102,127],"associated":[105],"with":[106,179],"low-entropy":[107],"bottlenecks":[108],"induced":[111],"probability":[112],"path,":[113],"where":[114],"routes":[118],"samples":[119],"through":[120],"overly":[121],"concentrated":[122],"intermediate":[123],"marginals.":[124],"Motivated":[125],"by":[126],"diagnosis,":[128],"introduce":[130],"stochastic":[132,160],"regularizer":[134],"hides":[136],"part":[137],"source":[140],"information":[141],"from":[142],"preserving":[147],"exact":[148],"endpoints.":[149],"The":[150],"resulting":[151],"regularization":[152],"gives":[153],"explicit":[155],"entropy":[156],"floor":[157],"training-path":[161],"marginals":[162],"empirically":[164],"suppresses":[165],"bottleneck":[167],"sampler,":[171],"making":[172],"joint":[173],"effective.":[176],"On":[177],"ImageNet-256x256":[178],"SiT":[180],"backbones,":[181],"our":[182],"method":[183],"consistently":[184],"improves":[185],"FID":[186],"across":[187],"model":[188],"scales,":[189],"extends":[190],"model-guidance":[192],"training,":[193],"leaves":[195],"inference-time":[197],"architecture":[198],"sampler":[200],"unchanged.":[201],"Code":[202],"available":[204],"at":[205],"https://github.com/lizeyu090312/traj_opt_paper":[206]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-10-09T00:00:00"}