{"id":"https://openalex.org/W4417114081","doi":"https://doi.org/10.18653/v1/2026.acl-long.425","title":"VAPO: End-to-end Slide-Enhanced Speech Recognition with Omni-modal Large Language Models","display_name":"VAPO: End-to-end Slide-Enhanced Speech Recognition with Omni-modal Large Language Models","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4417114081","doi":"https://doi.org/10.18653/v1/2026.acl-long.425"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.acl-long.425","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.425","pdf_url":"https://aclanthology.org/2026.acl-long.425.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.acl-long.425.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009685503","display_name":"Rui Hu","orcid":"https://orcid.org/0000-0003-0961-6760"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rui Hu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113152016","display_name":"Dongxu Qiu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Delai Qiu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100424577","display_name":"Yining Wang","orcid":"https://orcid.org/0000-0001-9410-0392"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yining Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043428124","display_name":"S M Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shengping Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5120721038","display_name":"Jitao Sang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jitao Sang","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":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02890817,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"9417","last_page":"9432"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.6883000135421753,"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":0.6883000135421753,"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":0.06069999933242798,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.04969999939203262,"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/pipeline","display_name":"Pipeline (software)","score":0.6822999715805054},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5652999877929688},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5633999705314636},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5242999792098999},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5196999907493591},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.5051000118255615},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4805999994277954},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.45010000467300415}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.796999990940094},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6822999715805054},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5652999877929688},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5633999705314636},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5408999919891357},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5242999792098999},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5196999907493591},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.5051000118255615},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4805999994277954},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.45010000467300415},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42309999465942383},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39879998564720154},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.3686999976634979},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.350600004196167},{"id":"https://openalex.org/C2777601897","wikidata":"https://www.wikidata.org/wiki/Q3409113","display_name":"Presentation (obstetrics)","level":2,"score":0.32170000672340393},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.27549999952316284},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2720000147819519},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.26809999346733093},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.2671000063419342},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2644999921321869},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2614000141620636},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.25999999046325684},{"id":"https://openalex.org/C111370547","wikidata":"https://www.wikidata.org/wiki/Q7451120","display_name":"Sensory cue","level":2,"score":0.25870001316070557},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2549999952316284},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.25119999051094055}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.425","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.425","pdf_url":"https://aclanthology.org/2026.acl-long.425.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2510.08618","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.08618","pdf_url":"https://arxiv.org/pdf/2510.08618","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:arXiv.org:2510.08618","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2510.08618","pdf_url":"https://arxiv.org/pdf/2510.08618","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,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2510.08618","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2510.08618","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,"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:10.18653/v1/2026.acl-long.425","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.425","pdf_url":"https://aclanthology.org/2026.acl-long.425.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320334978","display_name":"Beijing Nova Program","ror":"https://ror.org/034k14f91"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4417114081.pdf","grobid_xml":"https://content.openalex.org/works/W4417114081.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Omni-modal":[0],"large":[1],"language":[2],"models":[3,31],"(OLLMs)":[4],"offer":[5],"a":[6,22,33,75,86,112,124,131],"promising":[7],"end-to-end":[8],"solution":[9],"for":[10,128,136],"slideenhanced":[11],"speech":[12],"recognition":[13,160],"due":[14],"to":[15,43,61,66,89,116],"their":[16],"inherent":[17],"multimodal":[18],"capabilities.However,":[19],"we":[20,53,73,109],"found":[21],"fundamental":[23],"issue":[24],"faced":[25],"by":[26],"OLLMs:":[27],"Visual":[28],"Interference,":[29],"where":[30],"show":[32],"bias":[34],"towards":[35],"visible":[36],"text":[37],"over":[38],"auditory":[39],"signals,":[40],"causing":[41],"them":[42],"hallucinate":[44],"slide":[45],"content":[46],"that":[47,142],"was":[48],"never":[49],"spoken.To":[50],"address":[51,117],"this,":[52],"propose":[54],"Visually-Anchored":[55],"Policy":[56],"Optimization":[57],"(VAPO),":[58],"which":[59],"aims":[60],"reshape":[62],"models'":[63],"inference":[64,71],"process":[65],"follow":[67],"the":[68,79,96,118],"human-like":[69],"\"Look-then-Listen\"":[70],"chain.Specifically,":[72],"design":[74],"temporally":[76],"decoupled":[77],"policy:":[78],"model":[80],"first":[81],"extracts":[82],"visual":[83,146],"priors":[84],"in":[85,98,162],"<think>":[87],"block":[88],"serve":[90],"as":[91],"semantic":[92],"anchors,":[93],"then":[94],"generates":[95],"transcription":[97],"an":[99],"<answer>":[100],"block.The":[101],"policy":[102],"is":[103],"optimized":[104],"via":[105],"multi-objective":[106],"reinforcement":[107],"learning.Furthermore,":[108],"introduce":[110],"SlideASR-Bench,":[111],"comprehensive":[113],"benchmark":[114],"designed":[115],"scarcity":[119],"of":[120],"entity-rich":[121],"data,":[122],"comprising":[123],"large-scale":[125],"synthetic":[126],"corpus":[127],"training":[129],"and":[130,148,154],"challenging":[132],"real-world":[133],"test":[134],"set":[135],"evaluation.We":[137],"conduct":[138],"extensive":[139],"evaluations":[140],"demonstrating":[141],"VAPO":[143],"effectively":[144],"eliminates":[145],"interference":[147],"achieves":[149],"state-of-the-art":[150],"performance":[151],"on":[152],"SlideASR-Bench":[153],"public":[155],"datasets,":[156],"significantly":[157],"reducing":[158],"entity":[159],"errors":[161],"specialized":[163],"domains.":[164]},"counts_by_year":[],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-14T00:00:00"}