{"id":"https://openalex.org/W7204459612","doi":"https://doi.org/10.18653/2026.emnlp-main.1558","title":"V-Rubrics: Visual Faithfulness via Rubric-Based Reinforcement Learning","display_name":"V-Rubrics: Visual Faithfulness via Rubric-Based Reinforcement Learning","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7204459612","doi":"https://doi.org/10.18653/2026.emnlp-main.1558"},"language":"en","primary_location":{"id":"doi:10.18653/2026.emnlp-main.1558","doi":"https://doi.org/10.18653/2026.emnlp-main.1558","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.emnlp-main.1558","pdf_url":"https://aclanthology.org/2026.emnlp-main.1558.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","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://aclanthology.org/2026.emnlp-main.1558.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130214784","display_name":"Shulin Tian","orcid":"https://orcid.org/0000-0001-9915-9377","observed_orcids":["https://orcid.org/0000-0001-9915-9377"]},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Shulin Tian","raw_affiliation_strings":["A* STAR ,","S-Lab , Nanyang Technological University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"A* STAR ,","institution_ids":["https://openalex.org/I115228651"]},{"raw_affiliation_string":"S-Lab , Nanyang Technological University ,","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148432812","display_name":"Minglun Li","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Minglun Li","raw_affiliation_strings":["Independent Researcher ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Independent Researcher ,","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148451112","display_name":"Yuhao Dong","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yuhao Dong","raw_affiliation_strings":["S-Lab , Nanyang Technological University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"S-Lab , Nanyang Technological University ,","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126254230","display_name":"Hao Ding","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hao Ding","raw_affiliation_strings":["Independent Researcher ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Independent Researcher ,","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5143716129","display_name":"Jiarui Yao","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiarui Yao","raw_affiliation_strings":["UIUC * Equal Contributions. \u2021 Project Lead"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UIUC * Equal Contributions. \u2021 Project Lead","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015049935","display_name":"Haiwen Diao","orcid":"https://orcid.org/0000-0002-4156-5417","observed_orcids":["https://orcid.org/0000-0002-4156-5417"]},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Haiwen Diao","raw_affiliation_strings":["S-Lab , Nanyang Technological University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"S-Lab , Nanyang Technological University ,","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132964222","display_name":"Jingkang Yang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Jingkang Yang","raw_affiliation_strings":["S-Lab , Nanyang Technological University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"S-Lab , Nanyang Technological University ,","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124946895","display_name":"Hongyuan Zhu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Hongyuan Zhu","raw_affiliation_strings":["A* STAR ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"A* STAR ,","institution_ids":["https://openalex.org/I115228651"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129917825","display_name":"Ziwei Liu","orcid":"https://orcid.org/0000-0002-4220-5958","observed_orcids":["https://orcid.org/0000-0002-4220-5958"]},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Ziwei Liu","raw_affiliation_strings":["S-Lab , Nanyang Technological University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"S-Lab , Nanyang Technological University ,","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.9716,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.92302325,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"35524","last_page":"35543"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9994999766349792,"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":0.9994999766349792,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":9.999999747378752e-05,"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":0.0,"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/vision-language-models","display_name":"vision-language models","score":0.7590000033378601},{"id":"https://openalex.org/keywords/credit-assignment","display_name":"credit assignment","score":0.578000009059906},{"id":"https://openalex.org/keywords/visual-grounding","display_name":"visual grounding","score":0.6259999871253967},{"id":"https://openalex.org/keywords/reasoning-consistency","display_name":"reasoning consistency","score":0.6520000100135803},{"id":"https://openalex.org/keywords/instruction-following","display_name":"instruction following","score":0.9980000257492065},{"id":"https://openalex.org/keywords/partial-credit","display_name":"partial credit","score":0.621999979019165},{"id":"https://openalex.org/keywords/qwen3-vl","display_name":"Qwen3-VL","score":0.6990000009536743}],"concepts":[{"id":"https://openalex.org/C111640148","wikidata":"https://www.wikidata.org/wiki/Q847349","display_name":"Rubric","level":2,"score":0.8363000154495239},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6585000157356262},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5357999801635742},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5238000154495239},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5087000131607056},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5083000063896179},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4666999876499176},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.4618000090122223},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4406000077724457},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.41200000047683716},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41119998693466187},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.38499999046325684},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3625999987125397},{"id":"https://openalex.org/C190812933","wikidata":"https://www.wikidata.org/wiki/Q28923","display_name":"Chart","level":2,"score":0.353300005197525},{"id":"https://openalex.org/C148220186","wikidata":"https://www.wikidata.org/wiki/Q7111912","display_name":"Outcome (game theory)","level":2,"score":0.34950000047683716},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.33230000734329224},{"id":"https://openalex.org/C2777055276","wikidata":"https://www.wikidata.org/wiki/Q7936580","display_name":"Visual approach","level":2,"score":0.32989999651908875},{"id":"https://openalex.org/C2779321571","wikidata":"https://www.wikidata.org/wiki/Q7936605","display_name":"Visual learning","level":2,"score":0.3172999918460846},{"id":"https://openalex.org/C166088908","wikidata":"https://www.wikidata.org/wiki/Q308495","display_name":"Abductive reasoning","level":2,"score":0.28999999165534973},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.2872999906539917},{"id":"https://openalex.org/C193221554","wikidata":"https://www.wikidata.org/wiki/Q5153664","display_name":"Commonsense reasoning","level":2,"score":0.28290000557899475},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.26570001244544983},{"id":"https://openalex.org/C156325361","wikidata":"https://www.wikidata.org/wiki/Q1152864","display_name":"Grounded theory","level":3,"score":0.2653999924659729},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.26489999890327454},{"id":"https://openalex.org/C172367668","wikidata":"https://www.wikidata.org/wiki/Q6504956","display_name":"Data visualization","level":3,"score":0.2648000121116638},{"id":"https://openalex.org/C33762810","wikidata":"https://www.wikidata.org/wiki/Q461671","display_name":"Data integrity","level":2,"score":0.25929999351501465},{"id":"https://openalex.org/C189790780","wikidata":"https://www.wikidata.org/wiki/Q933932","display_name":"Horn clause","level":3,"score":0.25850000977516174},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.2581999897956848},{"id":"https://openalex.org/C2780069185","wikidata":"https://www.wikidata.org/wiki/Q7977945","display_name":"Equivalence (formal languages)","level":2,"score":0.25679999589920044},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.2547999918460846},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2522999942302704}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/2026.emnlp-main.1558","doi":"https://doi.org/10.18653/2026.emnlp-main.1558","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.emnlp-main.1558","pdf_url":"https://aclanthology.org/2026.emnlp-main.1558.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"},{"id":"pmh:oai:arXiv.org:2608.25580","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.25580","pdf_url":"https://arxiv.org/pdf/2608.25580","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.25580","doi":"https://doi.org/10.48550/arxiv.2608.25580","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.25580","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":"doi:10.18653/2026.emnlp-main.1558","doi":"https://doi.org/10.18653/2026.emnlp-main.1558","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.emnlp-main.1558","pdf_url":"https://aclanthology.org/2026.emnlp-main.1558.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/G3038162238","display_name":null,"funder_award_id":"MOE-T2EP20223-0002","funder_id":"https://openalex.org/F4320320751","funder_display_name":"Ministry of Education - Singapore"}],"funders":[{"id":"https://openalex.org/F4320320751","display_name":"Ministry of Education - Singapore","ror":"https://ror.org/01kcva023"},{"id":"https://openalex.org/F4320322724","display_name":"Ministry of Education, India","ror":"https://ror.org/048xjjh50"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204459612.pdf","grobid_xml":"https://content.openalex.org/works/W7204459612.grobid-xml"},"referenced_works_count":53,"referenced_works":["https://openalex.org/W2951298542","https://openalex.org/W4213213306","https://openalex.org/W4388685586","https://openalex.org/W4391631327","https://openalex.org/W4400479973","https://openalex.org/W4403370767","https://openalex.org/W4403791888","https://openalex.org/W4403883066","https://openalex.org/W4404330874","https://openalex.org/W4404350777","https://openalex.org/W4404987838","https://openalex.org/W4407794264","https://openalex.org/W4407806433","https://openalex.org/W4409362692","https://openalex.org/W4411120508","https://openalex.org/W4412944956","https://openalex.org/W4412945260","https://openalex.org/W4413145082","https://openalex.org/W4414281281","https://openalex.org/W4414565054","https://openalex.org/W4414586898","https://openalex.org/W4414689511","https://openalex.org/W4414854541","https://openalex.org/W4414876400","https://openalex.org/W4414886170","https://openalex.org/W4414886927","https://openalex.org/W4415085924","https://openalex.org/W4415123899","https://openalex.org/W4415153693","https://openalex.org/W4415536793","https://openalex.org/W4415795850","https://openalex.org/W4415796163","https://openalex.org/W4415971847","https://openalex.org/W4416053139","https://openalex.org/W4416053382","https://openalex.org/W4416540237","https://openalex.org/W4416550448","https://openalex.org/W4416651815","https://openalex.org/W4416780398","https://openalex.org/W4417011627","https://openalex.org/W4417298387","https://openalex.org/W4417515767","https://openalex.org/W6891934496","https://openalex.org/W6948439803","https://openalex.org/W6967053384","https://openalex.org/W7083483949","https://openalex.org/W7083819494","https://openalex.org/W7128505821","https://openalex.org/W7128781553","https://openalex.org/W7139939368","https://openalex.org/W7147548920","https://openalex.org/W7160273005","https://openalex.org/W7202178093"],"related_works":["https://openalex.org/W7139006983","https://openalex.org/W7162118248","https://openalex.org/W7166661772","https://openalex.org/W7214992552","https://openalex.org/W7131663269","https://openalex.org/W7101703515","https://openalex.org/W4416238817","https://openalex.org/W7160284950","https://openalex.org/W7166887968","https://openalex.org/W7160868197"],"abstract_inverted_index":{"Vision-language":[0],"models":[1],"can":[2,23],"produce":[3],"fluent":[4],"answers":[5,82],"that":[6,30,181,280],"are":[7,54,59,65,109,250],"insufficiently":[8],"grounded":[9,139,203],"in":[10,36,220,251],"the":[11,120,160,171,188,196,267,284],"visual":[12,52,215],"evidence:":[13],"a":[14,33,132,210,252,309],"single":[15],"unsupported":[16],"object,":[17],"chart":[18],"value,":[19],"or":[20,61],"intermediate":[21],"inference":[22],"undermine":[24],"an":[25,43,113],"otherwise":[26],"plausible":[27],"response.We":[28],"argue":[29],"this":[31,221],"is":[32,45,218,294],"credit-assignment":[34],"failure":[35],"multimodal":[37],"post-training.Scalar":[38],"outcome":[39],"rewards":[40],"indicate":[41],"whether":[42],"answer":[44,226],"acceptable,":[46],"but":[47],"do":[48],"not":[49],"identify":[50],"which":[51,56,62,72],"facts":[53],"grounded,":[55],"reasoning":[57,204],"steps":[58],"valid,":[60],"instruction":[63],"constraints":[64],"missed.We":[66],"introduce":[67],"Visual":[68,84,243],"Rubrics-Based":[69],"Reinforcement":[70],"Learning,":[71],"decomposes":[73],"reference":[74],"responses":[75],"into":[76],"atomic":[77],"propositions":[78],"and":[79,90,101,152,164,192,201,235,248,263],"scores":[80,151],"generated":[81],"along":[83],"Faithfulness":[85],"(VF),":[86],"Reasoning":[87,224],"Consistency":[88],"(RC),":[89],"Instruction":[91],"Following":[92],"(IF).The":[93],"resulting":[94],"rubric":[95,103,178],"items":[96],"provide":[97],"structured":[98,162],"partial":[99],"credit":[100,104],"localize":[102],"when":[105],"supporting":[106],"evidence":[107],"spans":[108],"available.We":[110],"first":[111],"obtain":[112],"SFT":[114,173,190],"checkpoint":[115,174],"by":[116,141],"fine-tuning":[117],"Qwen3-VL-8B-Instruct":[118],"on":[119,170,199],"public":[121],"OpenMMReasoner-SFT-874K":[122],"corpus,":[123],"adapting":[124],"OpenMMReasoner's":[125],"cold-start":[126],"data":[127],"recipe.We":[128],"construct":[129],"V-Rubrics":[130],"50K,":[131],"50,248-example":[133],"training":[134],"set":[135],"from":[136,149],"17":[137],"visually":[138,202],"sources,":[140],"applying":[142],"rule-based":[143],"filters":[144],"before":[145],"deriving":[146],"example":[147,156],"difficulty":[148],"rejection-sampling":[150],"then":[153],"annotating":[154],"every":[155],"with":[157,195],"Gemini-3-Pro":[158],"under":[159],"same":[161,172],"prompt":[163],"protocol.We":[165],"train":[166],"our":[167,182],"model":[168],"based":[169],"using":[175],"component-wise,":[176],"prefix-localized":[177],"credit.Experiments":[179],"show":[180,207],"rubricbased":[183],"GRPO":[184],"improves":[185],"over":[186],"both":[187],"shared":[189],"baseline":[191],"answer-only":[193],"GRPO,":[194],"largest":[197],"gains":[198],"knowledge-oriented":[200],"benchmarks.The":[205],"results":[206],"rubrics":[208],"as":[209],"useful":[211],"reward":[212],"abstraction":[213],"for":[214],"post-training.Q:":[216],"What":[217],"represented":[219],"image?Visual":[222],"grounding":[223],"&":[225],"1":[227],"Identifying":[228],"Objects":[229],"Identify":[230],"Sun":[231],"(A),":[232],"Earth":[233],"(C),":[234],"Moon":[236,249],"(D/G)":[237],"VF":[238,258],"Weight":[239,255,260],"5":[240,256,292],"Essential":[241,257],"2":[242],"Alignment":[244,276],"Recognize":[245],"Sun,":[246],"Earth,":[247],"straight":[253],"line.VF":[254],"Important":[259,275],"4":[261],"B":[262],"F":[264],"point":[265],"to":[266],"ocean":[268],"tidal":[269],"bulges.3":[270],"Tidal":[271],"Bulge":[272],"Obs.":[273],"RC":[274],"Effect":[277],"4Weight":[278],"4Explain":[279],"aligned":[281],"gravity":[282],"creates":[283],"highest":[285],"high":[286],"tides.":[287],"Select":[288],"Spring":[289],"Tide":[290,315],"IFWeight":[291],"EssentialAnswer":[293],"\"spring":[295],"tide\"":[296],"/":[297,300],"option":[298,301],"(3)":[299],"(D).":[302],"RCWeight":[303],"3":[304],"ImportantNeap":[305],"tide":[306],"would":[307],"require":[308],"90":[310],"\u00b0":[311],"Sun-Moon":[312],"angle.Distinguish":[313],"Neap":[314]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-08-28T00:00:00"}