{"id":"https://openalex.org/W7134224744","doi":"https://doi.org/10.48550/arxiv.2603.06397","title":"Efficient, Property-Aligned Fan-Out Retrieval via RL-Compiled Diffusion","display_name":"Efficient, Property-Aligned Fan-Out Retrieval via RL-Compiled Diffusion","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W7134224744","doi":"https://doi.org/10.48550/arxiv.2603.06397"},"language":null,"primary_location":{"id":"pmh:doi:10.48550/arxiv.2603.06397","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5128406208","display_name":"Pengcheng Jiang","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Jiang, Pengcheng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071459336","display_name":"Judith Yue Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Judith Yue","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128518129","display_name":"Moonkyung Ryu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ryu, Moonkyung","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128516146","display_name":"R. Lily Hu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hu, R. Lily","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128582494","display_name":"Kun Su","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Su, Kun","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128604875","display_name":"Zhong Yi Wan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wan, Zhong Yi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077331446","display_name":"Liam Hebert","orcid":"https://orcid.org/0000-0002-8990-1520"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hebert, Liam","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128396341","display_name":"Hao Peng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peng, Hao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128413300","display_name":"Jiawei Han","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Han, Jiawei","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068428403","display_name":"Dima Kuzmin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kuzmin, Dima","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5128555382","display_name":"Craig Boutilier","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Boutilier, Craig","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":11,"corresponding_author_ids":["https://openalex.org/A5128406208"],"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.2459000051021576,"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"}},"topics":[{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.2459000051021576,"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/T10028","display_name":"Topic Modeling","score":0.17720000445842743,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.13359999656677246,"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/inference","display_name":"Inference","score":0.5831000208854675},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.49160000681877136},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.39739999175071716},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.3578000068664551},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.3481000065803528},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.34369999170303345},{"id":"https://openalex.org/keywords/calibration","display_name":"Calibration","score":0.3425000011920929},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.32659998536109924}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.741599977016449},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5831000208854675},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.49160000681877136},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46889999508857727},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.42080000042915344},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39989998936653137},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.39739999175071716},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3652999997138977},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.3578000068664551},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3481000065803528},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.34369999170303345},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.3425000011920929},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.32659998536109924},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.3034000098705292},{"id":"https://openalex.org/C551230270","wikidata":"https://www.wikidata.org/wiki/Q4368942","display_name":"Data retrieval","level":2,"score":0.29490000009536743},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.2906999886035919},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.28850001096725464},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.27630001306533813},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.27390000224113464},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.2655999958515167},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.262800008058548},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.25440001487731934}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:doi:10.48550/arxiv.2603.06397","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Article"},{"id":"doi:10.48550/arxiv.2603.06397","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.06397","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:doi:10.48550/arxiv.2603.06397","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Many":[0],"modern":[1],"retrieval":[2,58,86,96,174],"problems":[3],"are":[4,38,42],"set-valued:":[5],"given":[6],"a":[7,14,33,126,131,146],"broad":[8],"intent,":[9],"the":[10,152],"system":[11],"must":[12],"return":[13],"collection":[15],"of":[16,155,165,188],"results":[17],"that":[18,171],"optimizes":[19],"higher-order":[20],"properties":[21],"(e.g.,":[22],"diversity,":[23],"coverage,":[24],"complementarity,":[25],"coherence)":[26],"while":[27,180],"remaining":[28],"grounded":[29],"with":[30,134],"respect":[31],"to":[32,62,66,150,177],"fixed":[34],"database.":[35],"Set-valued":[36],"objectives":[37,77],"typically":[39],"non-decomposable":[40],"and":[41,143,161],"not":[43],"captured":[44],"by":[45,185],"existing":[46],"supervised":[47],"(query,":[48],"content)":[49],"datasets":[50],"which":[51,117],"only":[52],"prioritize":[53],"top-1":[54],"retrieval.":[55],"Consequently,":[56],"fan-out":[57,85,100,132,183],"is":[59,87],"often":[60],"employed":[61],"generate":[63],"diverse":[64],"subqueries":[65],"retrieve":[67],"item":[68,167],"sets.":[69],"While":[70],"reinforcement":[71],"learning":[72],"(RL)":[73],"can":[74],"optimize":[75],"set-level":[76,136],"via":[78],"interaction,":[79],"deploying":[80],"an":[81,122,186],"RL-tuned":[82],"LLM":[83,133],"for":[84],"prohibitively":[88],"expensive":[89],"at":[90],"inference":[91],"time.":[92],"Conversely,":[93],"diffusion-based":[94],"generative":[95],"enables":[97],"efficient":[98],"single-pass":[99],"in":[101,125],"embedding":[102],"space,":[103],"but":[104],"requires":[105],"objective-aligned":[106],"training":[107,141],"targets.":[108],"To":[109],"address":[110],"these":[111],"issues,":[112],"we":[113,169],"propose":[114],"R4T":[115,172],"(Retrieve-for-Train),":[116],"uses":[118],"RL":[119],"once":[120],"as":[121],"objective":[123],"transducer":[124],"three-step":[127],"process:":[128],"(i)":[129],"train":[130,145],"composite":[135],"rewards,":[137],"(ii)":[138],"synthesize":[139],"objective-consistent":[140],"pairs,":[142],"(iii)":[144],"lightweight":[147],"diffusion":[148],"retriever":[149],"model":[151],"conditional":[153],"distribution":[154],"set-valued":[156],"outputs.":[157],"Across":[158],"large-scale":[159],"fashion":[160],"music":[162],"benchmarks":[163],"consisting":[164],"curated":[166],"sets,":[168],"show":[170],"improves":[173],"quality":[175],"relative":[176],"strong":[178],"baselines":[179],"reducing":[181],"query-time":[182],"latency":[184],"order":[187],"magnitude.":[189]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2026-03-10T00:00:00"}