{"id":"https://openalex.org/W7166863804","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1937","title":"Omni-R1: Towards the Unified Generative Paradigm for Multimodal Reasoning","display_name":"Omni-R1: Towards the Unified Generative Paradigm for Multimodal Reasoning","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166863804","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1937"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.1937","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1937","pdf_url":"https://aclanthology.org/2026.findings-acl.1937.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":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-acl.1937.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139730699","display_name":"Dongjie Cheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dongjie Cheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139716602","display_name":"Yongqi Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yongqi Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139715323","display_name":"Zhixin Ma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhixin Ma","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122435577","display_name":"Hongru Cai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hongru Cai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139737230","display_name":"Yupeng Hu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yupeng Hu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139828876","display_name":"Wenjie Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenjie Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139730596","display_name":"Liqiang Nie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liqiang Nie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139801984","display_name":"Wenjie Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenjie Li","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":0.85277689,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"38907","last_page":"38924"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.5935999751091003,"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"}},"topics":[{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.5935999751091003,"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/T11596","display_name":"Constraint Satisfaction and Optimization","score":0.11840000003576279,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.0406000018119812,"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/generative-grammar","display_name":"Generative grammar","score":0.46889999508857727},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.3075000047683716},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.2989000082015991},{"id":"https://openalex.org/keywords/case-based-reasoning","display_name":"Case-based reasoning","score":0.28130000829696655},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.2743000090122223}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.611299991607666},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5011000037193298},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.46889999508857727},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.3075000047683716},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2989000082015991},{"id":"https://openalex.org/C20162079","wikidata":"https://www.wikidata.org/wiki/Q1151406","display_name":"Case-based reasoning","level":2,"score":0.28130000829696655},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.27889999747276306},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.2743000090122223},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.25099998712539673},{"id":"https://openalex.org/C159032336","wikidata":"https://www.wikidata.org/wiki/Q2488768","display_name":"Non-monotonic logic","level":2,"score":0.24860000610351562}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.1937","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1937","pdf_url":"https://aclanthology.org/2026.findings-acl.1937.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":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.1937","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1937","pdf_url":"https://aclanthology.org/2026.findings-acl.1937.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":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322598","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166863804.pdf","grobid_xml":"https://content.openalex.org/works/W7166863804.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Multimodal":[0],"Large":[1],"Language":[2],"Models":[3],"(MLLMs)":[4],"are":[5,47,166],"making":[6],"significant":[7],"progress":[8],"in":[9,58],"multimodal":[10,22,43,49,76,81,121,144,162],"reasoning.Early":[11],"approaches":[12],"focus":[13],"on":[14,59,154],"pure":[15],"textbased":[16],"reasoning.More":[17],"recent":[18],"studies":[19],"have":[20],"incorporated":[21],"information":[23],"into":[24],"the":[25,89,118],"reasoning":[26,35,53,82,90,129,138],"steps;":[27],"however,":[28],"they":[29],"often":[30],"follow":[31],"a":[32,60,97,140,157],"single":[33],"task-specific":[34],"pattern,":[36],"which":[37,78,116],"limits":[38],"their":[39],"generalizability":[40],"across":[41,139],"various":[42],"tasks.In":[44],"fact,":[45],"there":[46],"numerous":[48],"tasks":[50],"requiring":[51],"diverse":[52,80],"skills,":[54],"such":[55],"as":[56],"zooming":[57],"specific":[61],"region":[62],"or":[63,150],"marking":[64],"an":[65,68],"object":[66],"within":[67],"image.To":[69],"address":[70],"this,":[71],"we":[72,113],"propose":[73],"unified":[74,136],"generative":[75,137,161],"reasoning,":[77],"unifies":[79],"skills":[83],"by":[84,123],"generating":[85],"intermediate":[86],"images":[87],"during":[88],"process.We":[91],"instantiate":[92],"this":[93],"paradigm":[94],"with":[95],"Omni-R1,":[96],"two-stage":[98],"SFT+RL":[99],"framework":[100],"featuring":[101],"perception":[102,106],"alignment":[103],"loss":[104],"and":[105,146,164],"reward,":[107],"thereby":[108],"enabling":[109],"functional":[110],"image":[111],"generation.Additionally,":[112],"introduce":[114],"Omni-R1-Zero,":[115],"eliminates":[117],"need":[119],"for":[120,160],"annotations":[122],"bootstrapping":[124],"step-wise":[125],"visualizations":[126],"from":[127],"text-only":[128],"data.Empirical":[130],"results":[131],"show":[132],"that":[133],"Omni-R1":[134,153],"achieves":[135],"wide":[141],"range":[142],"of":[143],"tasks,":[145],"Omni-R1-Zero":[147],"can":[148],"match":[149],"even":[151],"surpass":[152],"average,":[155],"suggesting":[156],"promising":[158],"direction":[159],"reasoning.Codes":[163],"checkpoints":[165],"available":[167],"at":[168],"Omni-R1.":[169]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}