{"id":"https://openalex.org/W7155420309","doi":"https://doi.org/10.48550/arxiv.2604.20755","title":"V-tableR1: Process-Supervised Multimodal Table Reasoning with Critic-Guided Policy Optimization","display_name":"V-tableR1: Process-Supervised Multimodal Table Reasoning with Critic-Guided Policy Optimization","publication_year":2026,"publication_date":"2026-04-22","ids":{"openalex":"https://openalex.org/W7155420309","doi":"https://doi.org/10.48550/arxiv.2604.20755"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.20755","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.20755","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":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.20755","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102172107","display_name":"Yubo Jiang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiang, Yubo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121687735","display_name":"Yitong An","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"An, Yitong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134382599","display_name":"Xin Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Xin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023291127","display_name":"Abudukelimu Wuerkaixi","orcid":"https://orcid.org/0000-0002-5609-606X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wuerkaixi, Abudukelimu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134440933","display_name":"Xuxin Cheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cheng, Xuxin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134403738","display_name":"Fengying Xie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xie, Fengying","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134412535","display_name":"Zhiguo Jiang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiang, Zhiguo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134377591","display_name":"Cao Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Cao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134386556","display_name":"Ke Zeng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zeng, Ke","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5134364490","display_name":"Haopeng Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Haopeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":10,"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":0.932200014591217,"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":0.932200014591217,"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":0.011800000444054604,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.008700000122189522,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/verifiable-secret-sharing","display_name":"Verifiable secret sharing","score":0.6884999871253967},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5722000002861023},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.515999972820282},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.5152999758720398},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.489300012588501},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.48429998755455017}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7457000017166138},{"id":"https://openalex.org/C85847156","wikidata":"https://www.wikidata.org/wiki/Q59015987","display_name":"Verifiable secret sharing","level":3,"score":0.6884999871253967},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5979999899864197},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5722000002861023},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.515999972820282},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.5152999758720398},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.489300012588501},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.48429998755455017},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4602999985218048},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.38850000500679016},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3686000108718872},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3562999963760376},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.3294000029563904},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.3091999888420105},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.26589998602867126}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.20755","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.20755","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":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.20755","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.20755","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":"article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.5247256755828857}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0,75],"introduce":[1],"V-tableR1,":[2],"a":[3,31,93,109,124],"process-supervised":[4],"reinforcement":[5],"learning":[6],"framework":[7],"that":[8,141],"elicits":[9],"rigorous,":[10],"verifiable":[11,160],"reasoning":[12,29,54],"from":[13,155],"multimodal":[14,153],"large":[15],"language":[16],"models":[17,170,176],"(MLLMs).":[18],"Current":[19],"MLLMs":[20],"trained":[21],"solely":[22],"on":[23,35,102,171],"final":[24],"outcomes":[25],"often":[26],"treat":[27],"visual":[28,59,89,105,145],"as":[30,86],"black":[32],"box,":[33],"relying":[34],"superficial":[36],"pattern":[37,157],"matching":[38,158],"rather":[39],"than":[40],"performing":[41],"rigorous":[42],"multi-step":[43],"inference.":[44],"While":[45],"Reinforcement":[46],"Learning":[47],"with":[48],"Verifiable":[49],"Rewards":[50],"could":[51],"enforce":[52],"transparent":[53],"trajectories,":[55],"extending":[56],"it":[57],"to":[58,97,159,178],"domains":[60],"remains":[61],"severely":[62],"hindered":[63],"by":[64,78,108],"the":[65,80,103],"ambiguity":[66],"of":[67,84],"grounding":[68],"abstract":[69],"logic":[70],"into":[71],"continuous":[72],"pixel":[73],"space.":[74],"solve":[76],"this":[77,114],"leveraging":[79],"deterministic":[81],"grid":[82],"structure":[83],"tables":[85],"an":[87],"ideal":[88],"testbed.":[90],"V-tableR1":[91,142,163],"employs":[92],"specialized":[94],"critic":[95],"VLM":[96],"provide":[98],"dense,":[99],"step-level":[100],"feedback":[101],"explicit":[104],"chain-of-thought":[106],"generated":[107],"policy":[110,132],"VLM.":[111],"To":[112],"optimize":[113],"system,":[115],"we":[116],"propose":[117],"Process-Guided":[118],"Direct":[119],"Alignment":[120],"Policy":[121],"Optimization":[122],"(PGPO),":[123],"novel":[125],"RL":[126],"algorithm":[127],"integrating":[128],"process":[129],"rewards,":[130],"decoupled":[131],"constraints,":[133],"and":[134,147,182],"length-aware":[135],"dynamic":[136],"sampling.":[137],"Extensive":[138],"evaluations":[139],"demonstrate":[140],"explicitly":[143],"penalizes":[144],"hallucinations":[146],"shortcut":[148],"guessing.":[149],"By":[150],"fundamentally":[151],"shifting":[152],"inference":[154],"black-box":[156],"logical":[161],"derivation,":[162],"4B":[164],"establishes":[165],"state-of-the-art":[166],"accuracy":[167],"among":[168],"open-source":[169],"complex":[172],"tabular":[173],"benchmarks,":[174],"outperforming":[175],"up":[177],"18x":[179],"its":[180,185],"size":[181],"improving":[183],"over":[184],"SFT":[186],"baseline":[187]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-04-24T00:00:00"}