{"id":"https://openalex.org/W7224673582","doi":"https://doi.org/10.18653/2026.emnlp-main.1935","title":"VIGOR: Outcome-Contrastive Visual Grounding for Multimodal Policy Optimization","display_name":"VIGOR: Outcome-Contrastive Visual Grounding for Multimodal Policy Optimization","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7224673582","doi":"https://doi.org/10.18653/2026.emnlp-main.1935"},"language":"en","primary_location":{"id":"doi:10.18653/2026.emnlp-main.1935","doi":"https://doi.org/10.18653/2026.emnlp-main.1935","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.emnlp-main.1935","pdf_url":"https://aclanthology.org/2026.emnlp-main.1935.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://aclanthology.org/2026.emnlp-main.1935.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5125971926","display_name":"Haohao Xu","orcid":"https://orcid.org/0009-0005-7754-3462","observed_orcids":["https://orcid.org/0009-0005-7754-3462"]},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haohao Xu","raw_affiliation_strings":["CACMS , Tianjin University ,","College of Management and Economics , Tianjin University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CACMS , Tianjin University ,","institution_ids":["https://openalex.org/I162868743"]},{"raw_affiliation_string":"College of Management and Economics , Tianjin University ,","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101263698","display_name":"Yuyao Ge","orcid":"https://orcid.org/0009-0001-3418-9679","observed_orcids":["https://orcid.org/0009-0001-3418-9679"]},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuyao Ge","raw_affiliation_strings":["Institute of Computing Technology , Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology , Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160147998","display_name":"Qiuyue Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiuyue Zhang","raw_affiliation_strings":["CACMS , Tianjin University ,","College of Management and Economics , Tianjin University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CACMS , Tianjin University ,","institution_ids":["https://openalex.org/I162868743"]},{"raw_affiliation_string":"College of Management and Economics , Tianjin University ,","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160100496","display_name":"Zhaoli Deng","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhaoli Deng","raw_affiliation_strings":["CICO Research Global Co., Ltd. ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CICO Research Global Co., Ltd. ,","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160118151","display_name":"HongLin Liu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"HongLin Liu","raw_affiliation_strings":["CICO Research Global Co., Ltd. ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CICO Research Global Co., Ltd. ,","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001534512","display_name":"Sheng Ang","orcid":"https://orcid.org/0000-0003-2434-277X","observed_orcids":["https://orcid.org/0000-0003-2434-277X"]},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sheng Ang","raw_affiliation_strings":["Hefei University of Technology ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hefei University of Technology ,","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160136698","display_name":"Likang Wu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Likang Wu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160099001","display_name":"Shenghua Liu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shenghua Liu","raw_affiliation_strings":["Institute of Computing Technology , Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology , Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5136073344","display_name":"Hongke Zhao","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hongke Zhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.91152522,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"44032","last_page":"44051"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9624000191688538,"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":0.9624000191688538,"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":0.01759999990463257,"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/T12031","display_name":"Speech and dialogue systems","score":0.0035000001080334187,"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/visual-grounding","display_name":"visual grounding","score":0.7829999923706055},{"id":"https://openalex.org/keywords/contrastive-learning","display_name":"contrastive learning","score":0.7580000162124634},{"id":"https://openalex.org/keywords/vision-language-models","display_name":"vision-language models","score":0.33799999952316284}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5920000076293945},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43309998512268066},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3564999997615814},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3384000062942505},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.2851000130176544},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2824999988079071},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.28029999136924744},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.27869999408721924},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2782000005245209},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.24130000174045563}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/2026.emnlp-main.1935","doi":"https://doi.org/10.18653/2026.emnlp-main.1935","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.emnlp-main.1935","pdf_url":"https://aclanthology.org/2026.emnlp-main.1935.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/2026.emnlp-main.1935","doi":"https://doi.org/10.18653/2026.emnlp-main.1935","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.emnlp-main.1935","pdf_url":"https://aclanthology.org/2026.emnlp-main.1935.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G4700137230","display_name":null,"funder_award_id":"62502340","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7688259989","display_name":null,"funder_award_id":"72471165","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322701","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32"},{"id":"https://openalex.org/F4320334897","display_name":"Natural Science Foundation of Anhui Province","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null},{"id":"https://openalex.org/F4320337401","display_name":"Division of Emerging Frontiers","ror":"https://ror.org/01tnvpc68"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7224673582.pdf","grobid_xml":"https://content.openalex.org/works/W7224673582.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7155058264","https://openalex.org/W7222371055","https://openalex.org/W7166812093","https://openalex.org/W7166838597","https://openalex.org/W7220949070","https://openalex.org/W3103542727","https://openalex.org/W3114660646","https://openalex.org/W7167424210","https://openalex.org/W4402671847","https://openalex.org/W7166872540"],"abstract_inverted_index":{"While":[0],"reinforcement":[1],"learning":[2],"with":[3,108],"verifiable":[4],"rewards":[5,13],"(RLVR)":[6],"has":[7],"advanced":[8],"multimodal":[9,100],"reasoning,":[10],"coarse":[11],"outcome":[12],"offer":[14],"limited":[15],"guidance":[16],"for":[17],"assigning":[18],"credit":[19],"to":[20,68,74,84],"visual":[21,37,66,81],"evidence.Analyzing":[22],"same-prompt":[23],"rollout":[24],"groups,":[25],"we":[26],"observe":[27],"that":[28,53],"different":[29],"outcomes":[30],"exhibit":[31],"distinct":[32],"temporal":[33,65],"patterns":[34],"of":[35],"measured":[36],"dependency":[38],"across":[39],"reasoning":[40,101],"segments.We":[41],"therefore":[42],"propose":[43],"VIGOR":[44,103,118],"(Visual":[45],"Grounding":[46],"Outcome-contrastive":[47],"Reinforcement),":[48],"a":[49],"policy":[50],"optimization":[51],"method":[52],"converts":[54],"these":[55],"group-wise":[56],"contrasts":[57,73],"into":[58],"fine-grained":[59],"supervision.VIGOR":[60],"constructs":[61],"outcome-conditioned":[62],"prototypes":[63],"from":[64],"fingerprints":[67],"reweight":[69],"trajectories,":[70],"uses":[71],"segment-level":[72],"prioritize":[75],"token":[76],"gradients,":[77],"and":[78,94,121],"allocates":[79],"the":[80,123],"budget":[82],"according":[83],"group":[85],"difficulty.It":[86],"requires":[87],"no":[88,96],"additional":[89],"annotations":[90],"or":[91],"reward":[92],"models":[93],"introduces":[95],"inference-time":[97],"overhead.Across":[98],"eight":[99,130],"benchmarks,":[102],"achieves":[104],"57.5%":[105],"average":[106],"accuracy":[107],"Qwen2.5-VL-7B,improving":[109],"over":[110],"VPPO":[111,127],"by":[112,132],"1.6":[113],"points.Controlled":[114],"experiments":[115],"further":[116],"validate":[117],"on":[119,128,135],"Qwen2.5-VL-3B":[120],"InternVL2.5-4B;on":[122],"latter,":[124],"it":[125],"outperforms":[126],"all":[129],"tasks":[131],"0.96":[133],"points":[134],"average.Our":[136],"code":[137],"is":[138],"publicly":[139],"available":[140],"at":[141],"https://github.com/":[142],"beck83879-bit/VIGOR.":[143],"25%":[144]},"counts_by_year":[],"updated_date":"2026-11-01T11:40:01.658920","created_date":"2026-10-30T00:00:00"}