{"id":"https://openalex.org/W7162330905","doi":"https://doi.org/10.48550/arxiv.2605.23655","title":"CVSearch: Empowering Multimodal LLMs with Cognitive Visual Search for High-Resolution Image Perception","display_name":"CVSearch: Empowering Multimodal LLMs with Cognitive Visual Search for High-Resolution Image Perception","publication_year":2026,"publication_date":"2026-05-22","ids":{"openalex":"https://openalex.org/W7162330905","doi":"https://doi.org/10.48550/arxiv.2605.23655"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.23655","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.23655","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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.2605.23655","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136782134","display_name":"Liupeng Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Liupeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136935237","display_name":"Haoqian Kang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kang, Haoqian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136945583","display_name":"Zhenyu Lu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu, Zhenyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136940748","display_name":"Jinpeng Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Jinpeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136931769","display_name":"Bin Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Bin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136902908","display_name":"Ke Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Ke","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5136963953","display_name":"Yaowei Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yaowei","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":0.7152000069618225,"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":0.7152000069618225,"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":0.13109999895095825,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.044199999421834946,"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-search","display_name":"Visual search","score":0.8051000237464905},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.4823000133037567},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.48080000281333923},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.444599986076355},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.42969998717308044},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.42750000953674316},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.3804999887943268},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.35589998960494995},{"id":"https://openalex.org/keywords/search-algorithm","display_name":"Search algorithm","score":0.329800009727478}],"concepts":[{"id":"https://openalex.org/C158495155","wikidata":"https://www.wikidata.org/wiki/Q2369151","display_name":"Visual search","level":2,"score":0.8051000237464905},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6610000133514404},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5281000137329102},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.4823000133037567},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.48080000281333923},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.444599986076355},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.42969998717308044},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.42750000953674316},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3804999887943268},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37389999628067017},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.35589998960494995},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3334999978542328},{"id":"https://openalex.org/C125583679","wikidata":"https://www.wikidata.org/wiki/Q755673","display_name":"Search algorithm","level":2,"score":0.329800009727478},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.32710000872612},{"id":"https://openalex.org/C166423231","wikidata":"https://www.wikidata.org/wiki/Q1891170","display_name":"Semantic search","level":3,"score":0.32589998841285706},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.320499986410141},{"id":"https://openalex.org/C19889080","wikidata":"https://www.wikidata.org/wiki/Q2835852","display_name":"Beam search","level":3,"score":0.30550000071525574},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.304500013589859},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.3025999963283539},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.30000001192092896},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.28369998931884766},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.27810001373291016},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.26489999890327454},{"id":"https://openalex.org/C60008888","wikidata":"https://www.wikidata.org/wiki/Q6031013","display_name":"Information bottleneck method","level":3,"score":0.2614000141620636},{"id":"https://openalex.org/C143587482","wikidata":"https://www.wikidata.org/wiki/Q1543216","display_name":"Iterative and incremental development","level":2,"score":0.25760000944137573},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.25679999589920044},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.2524999976158142},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2513999938964844}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.23655","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.23655","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.23655","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.23655","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":{"High-resolution":[0],"(HR)":[1],"image":[2],"perception":[3],"presents":[4],"a":[5,18,65,92,127,134],"key":[6],"bottleneck":[7],"for":[8],"multimodal":[9],"large":[10],"language":[11],"models":[12],"(MLLMs).":[13],"While":[14],"visual":[15],"search":[16,33,46,72,83,162],"offers":[17],"promising":[19],"solution,":[20],"existing":[21],"methods":[22],"struggle":[23],"with":[24],"the":[25,50],"trade-off":[26],"between":[27],"coverage":[28,48],"and":[29,55,89,141],"efficiency.":[30,163],"Visual":[31,135],"expert-assisted":[32,82],"is":[34,87,165],"efficient":[35,105,140],"but":[36],"prone":[37],"to":[38,113,138],"blind":[39],"spots":[40],"when":[41,84],"proposals":[42],"fail,":[43],"whereas":[44],"scan-based":[45],"guarantees":[47],"at":[49,167],"cost":[51],"of":[52,145],"computational":[53],"redundancy":[54],"semantic":[56],"fragmentation.":[57,123],"To":[58],"address":[59],"this":[60,104],"dilemma,":[61],"we":[62,125],"introduce":[63],"CVSearch,":[64],"training-free":[66],"adaptive":[67],"framework":[68],"that":[69,154],"dynamically":[70],"schedules":[71],"strategies":[73],"via":[74],"an":[75],"Assess-then-Search":[76],"workflow.":[77],"Specifically,":[78],"CVSearch":[79,155],"first":[80],"invokes":[81],"global":[85],"information":[86],"insufficient,":[88],"only":[90],"triggers":[91],"novel":[93],"semantic-aware":[94],"scanning":[95,106],"mechanism":[96],"upon":[97],"failure.":[98],"Distinct":[99],"from":[100],"rigid":[101],"grid":[102],"partitioning,":[103],"paradigm":[107],"incorporates":[108],"Semantic":[109],"Guided":[110],"Adaptive":[111],"Patching":[112],"decompose":[114],"images":[115],"into":[116],"semantically":[117],"consistent":[118],"regions,":[119],"effectively":[120],"mitigating":[121],"object":[122],"Furthermore,":[124],"devise":[126],"Dynamic":[128],"Bottom-Up":[129],"Search":[130],"strategy":[131],"driven":[132],"by":[133],"Complexity":[136],"prior":[137],"enable":[139],"precise":[142],"iterative":[143],"exploration":[144],"local":[146],"details.":[147],"Extensive":[148],"experiments":[149],"on":[150],"HR":[151],"benchmarks":[152],"demonstrate":[153],"achieves":[156],"state-of-the-art":[157],"accuracy":[158],"while":[159],"substantially":[160],"improving":[161],"Code":[164],"released":[166],"https://github.com/liliupeng28/ICML26-CVSearch.":[168]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-05-26T00:00:00"}