{"id":"https://openalex.org/W7128024955","doi":"https://doi.org/10.48550/arxiv.2602.05359","title":"Multimodal Latent Reasoning via Hierarchical Visual Cues Injection","display_name":"Multimodal Latent Reasoning via Hierarchical Visual Cues Injection","publication_year":2026,"publication_date":"2026-02-05","ids":{"openalex":"https://openalex.org/W7128024955","doi":"https://doi.org/10.48550/arxiv.2602.05359"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2602.05359","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2602.05359","pdf_url":"https://arxiv.org/pdf/2602.05359","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/2602.05359","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5125121441","display_name":"Yiming Zhang","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":"Zhang, Yiming","raw_affiliation_strings":["Nanyang Technological University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014522749","display_name":"Qiangyu Yan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan, Qiangyu","raw_affiliation_strings":["Huawei Noah's Ark Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Noah's Ark Lab","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022898952","display_name":"Borui Jiang","orcid":"https://orcid.org/0009-0008-8666-7178","observed_orcids":["https://orcid.org/0009-0008-8666-7178"]},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiang, Borui","raw_affiliation_strings":["Huawei Noah's Ark Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Noah's Ark Lab","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101828117","display_name":"Kai Han","orcid":"https://orcid.org/0000-0002-7995-9999","observed_orcids":["https://orcid.org/0000-0002-7995-9999"]},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Han, Kai","raw_affiliation_strings":["Huawei Noah's Ark Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Noah's Ark Lab","institution_ids":["https://openalex.org/I2250955327"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":7,"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/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"}},{"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-large-language-models","display_name":"multimodal large language models","score":0.9539999961853027},{"id":"https://openalex.org/keywords/visual-grounding","display_name":"visual grounding","score":0.7329999804496765},{"id":"https://openalex.org/keywords/slow-thinking","display_name":"slow thinking","score":0.6359999775886536},{"id":"https://openalex.org/keywords/hallucination-mitigation","display_name":"hallucination mitigation","score":0.6830000281333923},{"id":"https://openalex.org/keywords/multi-step-reasoning","display_name":"multi-step reasoning","score":0.6959999799728394},{"id":"https://openalex.org/keywords/test-time-scaling","display_name":"test-time scaling","score":0.625}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7217000126838684},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6100999712944031},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.609000027179718},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5450000166893005},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4408999979496002},{"id":"https://openalex.org/C144986985","wikidata":"https://www.wikidata.org/wiki/Q871236","display_name":"Hierarchical database model","level":2,"score":0.4129999876022339},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.3783000111579895},{"id":"https://openalex.org/C143587482","wikidata":"https://www.wikidata.org/wiki/Q1543216","display_name":"Iterative and incremental development","level":2,"score":0.3765000104904175},{"id":"https://openalex.org/C111370547","wikidata":"https://www.wikidata.org/wiki/Q7451120","display_name":"Sensory cue","level":2,"score":0.3614000082015991},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35510000586509705},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.3458999991416931},{"id":"https://openalex.org/C2779982483","wikidata":"https://www.wikidata.org/wiki/Q6094420","display_name":"Iterative refinement","level":2,"score":0.32899999618530273},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.31859999895095825},{"id":"https://openalex.org/C112933361","wikidata":"https://www.wikidata.org/wiki/Q2845258","display_name":"Probabilistic latent semantic analysis","level":2,"score":0.31290000677108765},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.3102000057697296},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.27720001339912415},{"id":"https://openalex.org/C124527596","wikidata":"https://www.wikidata.org/wiki/Q17029359","display_name":"Hierarchical control system","level":3,"score":0.2770000100135803},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.275299996137619},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.2709999978542328},{"id":"https://openalex.org/C20162079","wikidata":"https://www.wikidata.org/wiki/Q1151406","display_name":"Case-based reasoning","level":2,"score":0.2624000012874603},{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.26190000772476196}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2602.05359","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2602.05359","pdf_url":"https://arxiv.org/pdf/2602.05359","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.2602.05359","doi":"https://doi.org/10.48550/arxiv.2602.05359","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.05359","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:2602.05359","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2602.05359","pdf_url":"https://arxiv.org/pdf/2602.05359","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/W7128024955.pdf","grobid_xml":"https://content.openalex.org/works/W7128024955.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W2950104027","https://openalex.org/W3120043490","https://openalex.org/W4285255856","https://openalex.org/W4327810158","https://openalex.org/W4385473806","https://openalex.org/W4386185600","https://openalex.org/W4389523832","https://openalex.org/W4391631722","https://openalex.org/W4392011716","https://openalex.org/W4403799526","https://openalex.org/W4403853618","https://openalex.org/W4405783982","https://openalex.org/W4407310640","https://openalex.org/W4407794264","https://openalex.org/W4409356606","https://openalex.org/W4414488845","https://openalex.org/W4414565054","https://openalex.org/W4415796658","https://openalex.org/W4416283104","https://openalex.org/W4416780398","https://openalex.org/W6947991961","https://openalex.org/W7138915379"],"related_works":["https://openalex.org/W7092114685","https://openalex.org/W7164911105","https://openalex.org/W4417449755","https://openalex.org/W7127917507","https://openalex.org/W7131683544","https://openalex.org/W4414488845","https://openalex.org/W7141460672","https://openalex.org/W7161057124","https://openalex.org/W7160867944","https://openalex.org/W7160319041"],"abstract_inverted_index":{"The":[0],"advancement":[1],"of":[2,31,159],"multimodal":[3,56,61],"large":[4],"language":[5],"models":[6],"(MLLMs)":[7],"has":[8],"enabled":[9],"impressive":[10],"perception":[11],"capabilities.":[12],"However,":[13],"their":[14],"reasoning":[15,48,63,96],"process":[16,103],"often":[17],"remains":[18],"a":[19,52,70],"\"fast":[20],"thinking\"":[21,77],"paradigm,":[22],"reliant":[23],"on":[24,80],"end-to-end":[25],"generation":[26],"or":[27],"explicit,":[28],"language-centric":[29],"chains":[30],"thought":[32],"(CoT),":[33],"which":[34],"can":[35],"be":[36],"inefficient,":[37],"verbose,":[38],"and":[39,149],"prone":[40],"to":[41,112,126],"hallucination.":[42],"This":[43,122],"work":[44],"posits":[45],"that":[46,73,140,150],"robust":[47],"should":[49],"evolve":[50],"within":[51],"latent":[53,62,120,135],"space,":[54],"integrating":[55,151],"signals":[57],"seamlessly.":[58],"We":[59],"propose":[60],"via":[64],"HIerarchical":[65],"Visual":[66],"cuEs":[67],"injection":[68],"(\\emph{HIVE}),":[69],"novel":[71],"framework":[72],"instills":[74],"deliberate,":[75],"\"slow":[76],"without":[78],"depending":[79],"superficial":[81],"textual":[82],"rationales.":[83],"Our":[84],"method":[85],"recursively":[86],"extends":[87],"transformer":[88],"blocks,":[89],"creating":[90],"an":[91],"internal":[92],"loop":[93],"for":[94],"iterative":[95],"refinement.":[97],"Crucially,":[98],"it":[99],"injectively":[100],"grounds":[101],"this":[102],"with":[104],"hierarchical":[105,152],"visual":[106],"cues":[107],"from":[108],"global":[109],"scene":[110],"context":[111],"fine-grained":[113],"regional":[114],"details":[115],"directly":[116],"into":[117],"the":[118,124,133,156],"model's":[119,157],"representations.":[121],"enables":[123],"model":[125],"perform":[127],"grounded,":[128],"multi-step":[129],"inference":[130],"entirely":[131],"in":[132],"aligned":[134],"space.":[136],"Extensive":[137],"evaluations":[138],"demonstrate":[139],"test-time":[141],"scaling":[142],"is":[143],"effective":[144],"when":[145],"incorporating":[146],"vision":[147],"knowledge,":[148],"information":[153],"significantly":[154],"enhances":[155],"understanding":[158],"complex":[160],"scenes.":[161]},"counts_by_year":[{"year":2026,"cited_by_count":7}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-02-07T00:00:00"}