{"id":"https://openalex.org/W7124297002","doi":"https://doi.org/10.48550/arxiv.2601.09536","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":"2026-01-14","ids":{"openalex":"https://openalex.org/W7124297002","doi":"https://doi.org/10.48550/arxiv.2601.09536"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2601.09536","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2601.09536","pdf_url":"https://arxiv.org/pdf/2601.09536","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2601.09536","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5123921420","display_name":"Dongjie Cheng","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Cheng, Dongjie","raw_affiliation_strings":["The Hong Kong Polytechnic University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124020442","display_name":"Yongqi Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Li, Yongqi","raw_affiliation_strings":["The Hong Kong Polytechnic University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101558147","display_name":"Zhixin Ma","orcid":"https://orcid.org/0009-0002-4949-848X","observed_orcids":["https://orcid.org/0009-0002-4949-848X","https://orcid.org/0000-0002-9127-4175"]},"institutions":[{"id":"https://openalex.org/I79891267","display_name":"Singapore Management University","ror":"https://ror.org/050qmg959","country_code":"SG","type":"education","lineage":["https://openalex.org/I79891267"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Ma, Zhixin","raw_affiliation_strings":["Singapore Management University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Singapore Management University","institution_ids":["https://openalex.org/I79891267"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122435577","display_name":"Hongru Cai","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Cai, Hongru","raw_affiliation_strings":["The Hong Kong Polytechnic University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5118451721","display_name":"Yupeng Hu","orcid":"https://orcid.org/0000-0002-5653-8286","observed_orcids":["https://orcid.org/0000-0002-5653-8286"]},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hu, Yupeng","raw_affiliation_strings":["Shandong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shandong University","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125955307","display_name":"Wenjie Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Wenjie","raw_affiliation_strings":["University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125699777","display_name":"Liqiang Nie","orcid":"https://orcid.org/0000-0003-1476-0273","observed_orcids":["https://orcid.org/0000-0003-1476-0273"]},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nie, Liqiang","raw_affiliation_strings":["Harbin Institute of Technology (Shenzhen)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen)","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5138253501","display_name":"Wenjie Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Li, Wenjie","raw_affiliation_strings":["The Hong Kong Polytechnic University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University","institution_ids":["https://openalex.org/I14243506"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":5,"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":1.0,"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":1.0,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.0,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.0,"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/multimodal-reasoning","display_name":"multimodal reasoning","score":0.8920000195503235},{"id":"https://openalex.org/keywords/multimodal-large-language-models","display_name":"multimodal large language models","score":0.9509999752044678},{"id":"https://openalex.org/keywords/generative-reasoning","display_name":"generative reasoning","score":0.8539999723434448},{"id":"https://openalex.org/keywords/reinforcement-learning-from-human-feedback","display_name":"reinforcement learning from human feedback","score":0.6819999814033508},{"id":"https://openalex.org/keywords/zero-shot-reasoning","display_name":"zero-shot reasoning","score":0.48100000619888306},{"id":"https://openalex.org/keywords/image-zooming","display_name":"image zooming","score":0.40700000524520874},{"id":"https://openalex.org/keywords/object-labeling","display_name":"object marking","score":0.8370000123977661}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7109000086784363},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.7014999985694885},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.6488999724388123},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5730000138282776},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.5476999878883362},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4521999955177307},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.43209999799728394},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.423799991607666},{"id":"https://openalex.org/C207609745","wikidata":"https://www.wikidata.org/wiki/Q4944086","display_name":"Bootstrapping (finance)","level":2,"score":0.3912000060081482},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.38260000944137573},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.336899995803833},{"id":"https://openalex.org/C4441509","wikidata":"https://www.wikidata.org/wiki/Q6418787","display_name":"Multimodal therapy","level":2,"score":0.33399999141693115},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.3280999958515167},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.31700000166893005},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.3057999908924103},{"id":"https://openalex.org/C89288958","wikidata":"https://www.wikidata.org/wiki/Q7301504","display_name":"Reasoning system","level":2,"score":0.29409998655319214},{"id":"https://openalex.org/C166088908","wikidata":"https://www.wikidata.org/wiki/Q308495","display_name":"Abductive reasoning","level":2,"score":0.2903999984264374},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.2879999876022339},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.28630000352859497},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.2840000092983246},{"id":"https://openalex.org/C124913957","wikidata":"https://www.wikidata.org/wiki/Q1232548","display_name":"Zoom","level":3,"score":0.2802000045776367},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.26179999113082886},{"id":"https://openalex.org/C103057564","wikidata":"https://www.wikidata.org/wiki/Q4751139","display_name":"Analytic reasoning","level":3,"score":0.2540000081062317},{"id":"https://openalex.org/C44210515","wikidata":"https://www.wikidata.org/wiki/Q16968978","display_name":"Bespoke","level":2,"score":0.2538999915122986},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2502000033855438}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2601.09536","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2601.09536","pdf_url":"https://arxiv.org/pdf/2601.09536","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2601.09536","doi":"https://doi.org/10.48550/arxiv.2601.09536","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2601.09536","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2601.09536","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2601.09536","pdf_url":"https://arxiv.org/pdf/2601.09536","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7124297002.pdf","grobid_xml":"https://content.openalex.org/works/W7124297002.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W4285255856","https://openalex.org/W4382142077","https://openalex.org/W4387356472","https://openalex.org/W4397049097","https://openalex.org/W4400488544","https://openalex.org/W4402671151","https://openalex.org/W4403883066","https://openalex.org/W4403923795","https://openalex.org/W4404782847","https://openalex.org/W4414427071","https://openalex.org/W4416048517","https://openalex.org/W4416053139","https://openalex.org/W4416139080","https://openalex.org/W4417298857","https://openalex.org/W4417298859","https://openalex.org/W4417443023","https://openalex.org/W6910582812","https://openalex.org/W7133239970"],"related_works":["https://openalex.org/W7117967749","https://openalex.org/W4416097713","https://openalex.org/W4407036905","https://openalex.org/W7128535782","https://openalex.org/W7213584257","https://openalex.org/W4417307484","https://openalex.org/W7129338194","https://openalex.org/W4415926526","https://openalex.org/W4411113010","https://openalex.org/W4415331122"],"abstract_inverted_index":{"Multimodal":[0],"Large":[1],"Language":[2],"Models":[3],"(MLLMs)":[4],"are":[5,50],"making":[6],"significant":[7],"progress":[8],"in":[9,61],"multimodal":[10,24,45,52,80,85,127,151,169],"reasoning.":[11,18,170],"Early":[12],"approaches":[13],"focus":[14],"on":[15,62,161],"pure":[16],"text-based":[17],"More":[19],"recent":[20],"studies":[21],"have":[22],"incorporated":[23],"information":[25],"into":[26],"the":[27,93,124],"reasoning":[28,37,56,86,94,135,145],"steps;":[29],"however,":[30],"they":[31],"often":[32],"follow":[33],"a":[34,63,102,147,164],"single":[35],"task-specific":[36],"pattern,":[38],"which":[39,82,122],"limits":[40],"their":[41],"generalizability":[42],"across":[43,146],"various":[44],"tasks.":[46],"In":[47],"fact,":[48],"there":[49],"numerous":[51],"tasks":[53],"requiring":[54],"diverse":[55,84],"skills,":[57],"such":[58],"as":[59],"zooming":[60],"specific":[64],"region":[65],"or":[66,157],"marking":[67],"an":[68,71],"object":[69],"within":[70],"image.":[72],"To":[73],"address":[74],"this,":[75],"we":[76,119],"propose":[77],"unified":[78,143],"generative":[79,144,168],"reasoning,":[81],"unifies":[83],"skills":[87],"by":[88,129],"generating":[89],"intermediate":[90],"images":[91],"during":[92],"process.":[95],"We":[96],"instantiate":[97],"this":[98],"paradigm":[99],"with":[100],"Omni-R1,":[101],"two-stage":[103],"SFT+RL":[104],"framework":[105],"featuring":[106],"perception":[107,111],"alignment":[108],"loss":[109],"and":[110,153],"reward,":[112],"thereby":[113],"enabling":[114],"functional":[115],"image":[116],"generation.":[117],"Additionally,":[118],"introduce":[120],"Omni-R1-Zero,":[121],"eliminates":[123],"need":[125],"for":[126,167],"annotations":[128],"bootstrapping":[130],"step-wise":[131],"visualizations":[132],"from":[133],"text-only":[134],"data.":[136],"Empirical":[137],"results":[138],"show":[139],"that":[140],"Omni-R1":[141,160],"achieves":[142],"wide":[148],"range":[149],"of":[150],"tasks,":[152],"Omni-R1-Zero":[154],"can":[155],"match":[156],"even":[158],"surpass":[159],"average,":[162],"suggesting":[163],"promising":[165],"direction":[166]},"counts_by_year":[{"year":2026,"cited_by_count":5}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-01-16T00:00:00"}
