{"id":"https://openalex.org/W7134914451","doi":"https://doi.org/10.48550/arxiv.2603.09478","title":"MORE-R1: Guiding LVLM for Multimodal Object-Entity Relation Extraction via Stepwise Reasoning with Reinforcement Learning","display_name":"MORE-R1: Guiding LVLM for Multimodal Object-Entity Relation Extraction via Stepwise Reasoning with Reinforcement Learning","publication_year":2026,"publication_date":"2026-03-10","ids":{"openalex":"https://openalex.org/W7134914451","doi":"https://doi.org/10.48550/arxiv.2603.09478"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.09478","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.09478","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.2603.09478","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5128753334","display_name":"Xiang Yuan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuan, Xiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128710356","display_name":"Xu Chu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chu, Xu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128745927","display_name":"Xinrong Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Xinrong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128783062","display_name":"Haochen Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Haochen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128697608","display_name":"Zonghong Dai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dai, Zonghong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089028342","display_name":"Hongcheng Fan","orcid":"https://orcid.org/0000-0001-9038-7998"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fan, Hongcheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128703274","display_name":"Xiaoyue Yuan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuan, Xiaoyue","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128706368","display_name":"Weiping Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Weiping","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5128779827","display_name":"Tong Mo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mo, Tong","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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9603000283241272,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9603000283241272,"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/T10028","display_name":"Topic Modeling","score":0.014499999582767487,"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":0.005100000184029341,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7418000102043152},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7095999717712402},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5891000032424927},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5813999772071838},{"id":"https://openalex.org/keywords/relationship-extraction","display_name":"Relationship extraction","score":0.4756999909877777},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.428600013256073},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.42329999804496765},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.3531999886035919}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7595999836921692},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7418000102043152},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7095999717712402},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7095000147819519},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5891000032424927},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5878999829292297},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5813999772071838},{"id":"https://openalex.org/C153604712","wikidata":"https://www.wikidata.org/wiki/Q7310755","display_name":"Relationship extraction","level":3,"score":0.4756999909877777},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.428600013256073},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.42329999804496765},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3531999886035919},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.3449999988079071},{"id":"https://openalex.org/C20162079","wikidata":"https://www.wikidata.org/wiki/Q1151406","display_name":"Case-based reasoning","level":2,"score":0.31839999556541443},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.30559998750686646},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.3005000054836273},{"id":"https://openalex.org/C83725634","wikidata":"https://www.wikidata.org/wiki/Q7268699","display_name":"Qualitative reasoning","level":2,"score":0.28060001134872437},{"id":"https://openalex.org/C89288958","wikidata":"https://www.wikidata.org/wiki/Q7301504","display_name":"Reasoning system","level":2,"score":0.27889999747276306},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.26510000228881836},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.2597000002861023},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.2590999901294708},{"id":"https://openalex.org/C37335422","wikidata":"https://www.wikidata.org/wiki/Q6888134","display_name":"Model-based reasoning","level":3,"score":0.25870001316070557},{"id":"https://openalex.org/C86827895","wikidata":"https://www.wikidata.org/wiki/Q7098582","display_name":"Opportunistic reasoning","level":4,"score":0.25040000677108765}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.09478","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.09478","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.2603.09478","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.09478","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Multimodal":[0],"Object-Entity":[1],"Relation":[2],"Extraction":[3],"(MORE)":[4],"is":[5],"a":[6,66,92,107,127,164],"challenging":[7],"task":[8,49,88],"in":[9,46],"information":[10],"extraction":[11,44],"research.":[12],"It":[13],"aims":[14],"to":[15,41,78,84,124,136,143,168],"identify":[16],"relations":[17],"between":[18],"visual":[19],"objects":[20],"and":[21,28,50,55,106,171],"textual":[22],"entities,":[23],"requiring":[24],"complex":[25,43],"multimodal":[26],"understanding":[27],"cross-modal":[29],"reasoning":[30,57,73,112,134,147,175],"abilities.":[31],"Existing":[32],"methods,":[33],"mainly":[34],"classification-based":[35],"or":[36],"generation-based":[37],"without":[38],"reasoning,":[39],"struggle":[40],"handle":[42],"scenarios":[45],"the":[47,86,116,137,141,150,155,183],"MORE":[48,87,138,184],"suffer":[51],"from":[52],"limited":[53],"scalability":[54],"intermediate":[56],"transparency.":[58],"To":[59],"address":[60,85],"these":[61],"challenges,":[62],"we":[63,119,153],"propose":[64],"MORE-R1,":[65],"novel":[67],"model":[68,142],"that":[69,187],"introduces":[70],"explicit":[71],"stepwise":[72,133],"with":[74,102,163,192],"Reinforcement":[75],"Learning":[76],"(RL)":[77],"enable":[79],"Large":[80],"Vision-Language":[81],"Model":[82],"(LVLM)":[83],"effectively.":[89],"MORE-R1":[90,188],"integrates":[91],"two-stage":[93],"training":[94,100,170],"process,":[95],"including":[96],"an":[97,121,145],"initial":[98,117],"cold-start":[99],"stage":[101,110],"Supervised":[103],"Fine-Tuning":[104],"(SFT)":[105],"subsequent":[108,151],"RL":[109,161],"for":[111],"ability":[113,176],"optimization.":[114],"In":[115,149],"stage,":[118,152],"design":[120],"efficient":[122],"way":[123],"automatically":[125],"construct":[126],"high-quality":[128],"SFT":[129],"dataset":[130],"containing":[131],"fine-grained":[132],"tailored":[135],"task,":[139],"enabling":[140],"learn":[144],"effective":[146],"paradigm.":[148],"employ":[154],"Group":[156],"Relative":[157],"Policy":[158],"Optimization":[159],"(GRPO)":[160],"algorithm":[162],"Progressive":[165],"Sample-Mixing":[166],"Strategy":[167],"stabilize":[169],"further":[172],"enhance":[173],"model's":[174],"on":[177,182],"hard":[178],"samples.":[179],"Comprehensive":[180],"experiments":[181],"benchmark":[185],"demonstrate":[186],"achieves":[189],"state-of-the-art":[190],"performance":[191],"significant":[193],"improvement":[194],"over":[195],"baselines.":[196]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-03-12T00:00:00"}