{"id":"https://openalex.org/W7140174797","doi":"https://doi.org/10.48550/arxiv.2603.21754","title":"Let's Think with Images Efficiently! An Interleaved-Modal Chain-of-Thought Reasoning Framework with Dynamic and Precise Visual Thoughts","display_name":"Let's Think with Images Efficiently! An Interleaved-Modal Chain-of-Thought Reasoning Framework with Dynamic and Precise Visual Thoughts","publication_year":2026,"publication_date":"2026-03-23","ids":{"openalex":"https://openalex.org/W7140174797","doi":"https://doi.org/10.48550/arxiv.2603.21754"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.21754","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.21754","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":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.21754","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Liu, Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Xu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Zhang, Yongheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Yongheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Chen, Qiguang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Qiguang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Li, Yao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Yao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Wang, Sheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Sheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Qin, Libo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qin, Libo","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":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":0.738099992275238,"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":0.738099992275238,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.0478999987244606,"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":0.04490000009536743,"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/visual-reasoning","display_name":"Visual reasoning","score":0.6642000079154968},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.6327999830245972},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.5309000015258789},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.41179999709129333},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.3790999948978424},{"id":"https://openalex.org/keywords/human-visual-system-model","display_name":"Human visual system model","score":0.36239999532699585},{"id":"https://openalex.org/keywords/visual-perception","display_name":"Visual perception","score":0.3578000068664551}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7786999940872192},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.6642000079154968},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.6327999830245972},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5637999773025513},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.5309000015258789},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.41179999709129333},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.37940001487731934},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.3790999948978424},{"id":"https://openalex.org/C160086991","wikidata":"https://www.wikidata.org/wiki/Q5939193","display_name":"Human visual system model","level":3,"score":0.36239999532699585},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.3578000068664551},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.35440000891685486},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3529999852180481},{"id":"https://openalex.org/C2780103172","wikidata":"https://www.wikidata.org/wiki/Q1309721","display_name":"Visual Objects","level":3,"score":0.29809999465942383},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.27480000257492065},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.2727000117301941},{"id":"https://openalex.org/C103057564","wikidata":"https://www.wikidata.org/wiki/Q4751139","display_name":"Analytic reasoning","level":3,"score":0.2718999981880188},{"id":"https://openalex.org/C158495155","wikidata":"https://www.wikidata.org/wiki/Q2369151","display_name":"Visual search","level":2,"score":0.25850000977516174},{"id":"https://openalex.org/C33326189","wikidata":"https://www.wikidata.org/wiki/Q17092450","display_name":"Information integration","level":2,"score":0.25380000472068787}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.21754","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.21754","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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.21754","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.21754","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":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recently,":[0],"Interleaved-modal":[1,71],"Chain-of-Thought":[2,72],"(ICoT)":[3],"reasoning":[4,73,97],"has":[5],"achieved":[6],"remarkable":[7],"success":[8],"by":[9],"leveraging":[10],"both":[11],"multimodal":[12],"inputs":[13,94],"and":[14,48,51,60,76,101,113,121],"outputs,":[15],"attracting":[16],"increasing":[17],"attention.":[18],"While":[19],"achieving":[20],"promising":[21],"performance,":[22],"current":[23],"ICoT":[24,150],"methods":[25],"still":[26],"suffer":[27],"from":[28],"two":[29,83],"major":[30],"limitations:":[31],"(1)":[32,86],"Static":[33],"Visual":[34,54,78,88,106],"Thought":[35,55,89,107],"Positioning,":[36],"which":[37,57,81],"statically":[38],"inserts":[39],"visual":[40,63,93,110],"information":[41],"at":[42],"fixed":[43],"steps,":[44],"resulting":[45],"in":[46,144],"inefficient":[47],"inflexible":[49],"reasoning;":[50],"(2)":[52,104],"Broken":[53],"Representation,":[56],"involves":[58],"discontinuous":[59],"semantically":[61,111],"incoherent":[62],"tokens.":[64],"To":[65],"address":[66],"these":[67],"limitations,":[68],"we":[69],"introduce":[70],"with":[74],"Dynamic":[75,87],"Precise":[77,105],"Thoughts":[79],"(DaP-ICoT),":[80],"incorporates":[82],"key":[84],"components:":[85],"Integration":[90],"adaptively":[91],"introduces":[92],"based":[95],"on":[96],"needs,":[98],"reducing":[99],"redundancy":[100],"improving":[102],"efficiency.":[103],"Guidance":[108],"ensures":[109],"coherent":[112],"contextually":[114],"aligned":[115],"representations.":[116],"Experiments":[117],"across":[118],"multiple":[119],"benchmarks":[120],"models":[122],"demonstrate":[123],"that":[124],"DaP-ICoT":[125,131],"achieves":[126],"state-of-the-art":[127],"performance.":[128],"In":[129],"addition,":[130],"significantly":[132],"reduces":[133],"the":[134],"number":[135],"of":[136],"inserted":[137],"images,":[138],"leading":[139],"to":[140],"a":[141],"72.6%":[142],"decrease":[143],"token":[145],"consumption,":[146],"enabling":[147],"more":[148],"efficient":[149],"reasoning.":[151]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-03-25T00:00:00"}