{"id":"https://openalex.org/W7163384596","doi":"https://doi.org/10.48550/arxiv.2606.03119","title":"GuidedBridge: Training-freely Improving Bridge Models with Prior Guidance","display_name":"GuidedBridge: Training-freely Improving Bridge Models with Prior Guidance","publication_year":2026,"publication_date":"2026-06-02","ids":{"openalex":"https://openalex.org/W7163384596","doi":"https://doi.org/10.48550/arxiv.2606.03119"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.03119","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.03119","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":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2606.03119","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5137733702","display_name":"Zehua Chen (12054)","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Zehua","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101267885","display_name":"Yang Yucheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Yucheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137782110","display_name":"Binjie Yuan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuan, Binjie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137784980","display_name":"Kaiwen Zheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zheng, Kaiwen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137726146","display_name":"Jun Liu (42548)","orcid":"https://orcid.org/0009-0007-2372-3139"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Jun S.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5137739822","display_name":"Jun Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Jun","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":false,"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":0.926800012588501,"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":0.926800012588501,"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":0.04699999839067459,"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/T11751","display_name":"Lattice Boltzmann Simulation Studies","score":0.0017999999690800905,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/bridge","display_name":"Bridge (graph theory)","score":0.6413000226020813},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.6019999980926514},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.6004999876022339},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.595300018787384},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4699999988079071},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.46810001134872437},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.4221000075340271},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4140999913215637}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7196000218391418},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.6413000226020813},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.6019999980926514},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6004999876022339},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.595300018787384},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5612000226974487},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4699999988079071},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.46810001134872437},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.4221000075340271},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4140999913215637},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3874000012874603},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3824000060558319},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.3537999987602234},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.33640000224113464},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.3361999988555908},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.31209999322891235},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.29750001430511475},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.289000004529953},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.27619999647140503},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2728999853134155},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2696000039577484},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.2685999870300293},{"id":"https://openalex.org/C184408114","wikidata":"https://www.wikidata.org/wiki/Q1502022","display_name":"Generative Design","level":3,"score":0.2612999975681305}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.03119","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.03119","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":"doi:10.48550/arxiv.2606.03119","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.03119","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":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.461357057094574}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Guidance":[0,57],"methods,":[1],"such":[2],"as":[3,46,157],"classifier-free":[4],"guidance":[5,53,114,119],"(CFG)":[6],"and":[7,74,89,110,123,153],"auto-guidance":[8],"(AG),":[9],"have":[10,20],"advanced":[11],"noise-to-data":[12],"generation":[13],"in":[14,106,135],"diffusion":[15],"models.":[16],"Recently,":[17],"bridge":[18,52,69,108,128,180],"models":[19,181],"introduced":[21],"a":[22,50,62,94,140,147,158],"data-to-data":[23],"generative":[24,129,159],"process":[25,109],"that":[26,173],"can":[27],"exploit":[28],"an":[29],"instructive":[30],"clean":[31],"prior.":[32],"In":[33],"this":[34],"work,":[35],"inspired":[36],"by":[37],"previous":[38],"methods":[39,176],"creating":[40],"quality":[41],"difference":[42],"between":[43],"denoising":[44,77],"results":[45],"guidance,":[47],"we":[48,60,80,98,138],"propose":[49],"training-free":[51],"method,":[54],"termed":[55],"Prior":[56],"(PG).":[58],"Specifically,":[59],"introduce":[61],"weak":[63],"prior,":[64],"which":[65,116,144],"is":[66],"unseen":[67],"during":[68],"pre-training,":[70],"hindering":[71],"prior":[72,86,91,104,113,133,160],"exploitation":[73,92,105,134],"thereby":[75],"degrading":[76],"result.":[78],"Then,":[79],"contrast":[81],"it":[82,156],"with":[83,127,161],"the":[84,100,107,118],"seen":[85],"to":[87,121],"highlight":[88],"enhance":[90],"via":[93,151],"scaling":[95],"factor.":[96],"Moreover,":[97],"analyze":[99],"underlying":[101],"mechanism":[102],"of":[103],"design":[111],"frequency-modulated":[112],"(FMPG),":[115],"tailors":[117],"scale":[120],"low-":[122],"high-frequency":[124],"bands":[125],"coherent":[126],"dynamics.":[130],"To":[131],"address":[132],"image":[136,184],"in-painting,":[137],"develop":[139],"cascaded":[141],"framework,":[142],"CFG-FMPG,":[143],"first":[145],"generates":[146],"noisy":[148],"hidden":[149],"representation":[150],"CFG":[152],"then":[154],"exploits":[155],"FMPG,":[162],"fulfilling":[163],"their":[164],"complementary":[165],"strengths":[166],"without":[167],"compromising":[168],"inference":[169],"efficiency.":[170],"Experiments":[171],"demonstrate":[172],"our":[174],"PG":[175],"consistently":[177],"improve":[178],"pre-trained":[179],"across":[182],"diverse":[183],"translation":[185],"tasks.":[186]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-04T00:00:00"}