{"id":"https://openalex.org/W4406933350","doi":"https://doi.org/10.1109/iccv51701.2025.02184","title":"FALCON: Resolving Visual Redundancy and Fragmentation in High-Resolution Multimodal Large Language Models via Visual Registers","display_name":"FALCON: Resolving Visual Redundancy and Fragmentation in High-Resolution Multimodal Large Language Models via Visual Registers","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4406933350","doi":"https://doi.org/10.1109/iccv51701.2025.02184"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.02184","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02184","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2501.16297","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103115471","display_name":"Renshan Zhang","orcid":"https://orcid.org/0000-0003-1833-9996"},"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":"Renshan Zhang","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":"middle","author":{"id":"https://openalex.org/A5064879510","display_name":"Rui Shao","orcid":"https://orcid.org/0000-0002-5405-0033"},"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":"Rui Shao","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":"middle","author":{"id":"https://openalex.org/A5070971328","display_name":"Gongwei Chen","orcid":"https://orcid.org/0009-0009-1803-4878"},"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":"Gongwei Chen","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":"middle","author":{"id":null,"display_name":"Miao Zhang","orcid":null},"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":"Miao Zhang","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":"middle","author":{"id":"https://openalex.org/A5001993403","display_name":"Kaiwen Zhou","orcid":"https://orcid.org/0000-0002-1943-0612"},"institutions":[{"id":"https://openalex.org/I4210159102","display_name":"Huawei Technologies (Sweden)","ror":"https://ror.org/0500fyd17","country_code":"SE","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210159102"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Kaiwen Zhou","raw_affiliation_strings":["Huawei Noah&#x0027;s Ark Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Noah&#x0027;s Ark Lab","institution_ids":["https://openalex.org/I4210159102"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075938343","display_name":"Weili Guan","orcid":"https://orcid.org/0000-0002-5658-5509"},"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":"Weili Guan","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/A5038612499","display_name":"Liqiang Nie","orcid":"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":"Liqiang Nie","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"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00572252,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"23530","last_page":"23540"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.992900013923645,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.992900013923645,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9725000262260437,"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":0.9609000086784363,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/fragmentation","display_name":"Fragmentation (computing)","score":0.7062585353851318},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.6872388124465942},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5940762162208557},{"id":"https://openalex.org/keywords/falcon","display_name":"Falcon","score":0.5416560173034668},{"id":"https://openalex.org/keywords/visual-language","display_name":"Visual language","score":0.4739258885383606},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3382194936275482},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.21110284328460693},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1574077010154724},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.06831571459770203},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.05626371502876282}],"concepts":[{"id":"https://openalex.org/C191015642","wikidata":"https://www.wikidata.org/wiki/Q1132459","display_name":"Fragmentation (computing)","level":2,"score":0.7062585353851318},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.6872388124465942},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5940762162208557},{"id":"https://openalex.org/C2775845381","wikidata":"https://www.wikidata.org/wiki/Q43489","display_name":"Falcon","level":2,"score":0.5416560173034668},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.4739258885383606},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3382194936275482},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.21110284328460693},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1574077010154724},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.06831571459770203},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.05626371502876282}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.02184","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02184","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2501.16297","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2501.16297","pdf_url":"https://arxiv.org/pdf/2501.16297","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2501.16297","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2501.16297","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":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2501.16297","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2501.16297","pdf_url":"https://arxiv.org/pdf/2501.16297","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2993895108","display_name":null,"funder_award_id":"2024A1515010147","funder_id":"https://openalex.org/F4320337111","funder_display_name":"Basic and Applied Basic Research Foundation of Guangdong Province"},{"id":"https://openalex.org/G427697057","display_name":null,"funder_award_id":"KQTD20240729102207002","funder_id":"https://openalex.org/F4320325195","funder_display_name":"Korean Dermatological Association"},{"id":"https://openalex.org/G4633876510","display_name":null,"funder_award_id":"BG2024041","funder_id":"https://openalex.org/F4320327912","funder_display_name":"Higher Education Discipline Innovation Project"},{"id":"https://openalex.org/G5011900912","display_name":null,"funder_award_id":"62306090,U24A20328","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5835197607","display_name":null,"funder_award_id":"L254018","funder_id":"https://openalex.org/F4320322919","funder_display_name":"Natural Science Foundation of Beijing Municipality"},{"id":"https://openalex.org/G662850918","display_name":null,"funder_award_id":"2024M764192","funder_id":"https://openalex.org/F4320321106","funder_display_name":"Ministry of Education of the People's Republic of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321106","display_name":"Ministry of Education of the People's Republic of China","ror":"https://ror.org/01mv9t934"},{"id":"https://openalex.org/F4320322919","display_name":"Natural Science Foundation of Beijing Municipality","ror":null},{"id":"https://openalex.org/F4320325195","display_name":"Korean Dermatological Association","ror":"https://ror.org/03y50tm06"},{"id":"https://openalex.org/F4320327912","display_name":"Higher Education Discipline Innovation Project","ror":null},{"id":"https://openalex.org/F4320337111","display_name":"Basic and Applied Basic Research Foundation of Guangdong Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2559910745","https://openalex.org/W1996171346","https://openalex.org/W3012004699","https://openalex.org/W2316698445","https://openalex.org/W73822458","https://openalex.org/W3029030103","https://openalex.org/W2478859663","https://openalex.org/W4251274518","https://openalex.org/W2954058429","https://openalex.org/W3155425594"],"abstract_inverted_index":{"The":[0],"incorporation":[1],"of":[2,71,84,100,128,185,204],"high-resolution":[3,23,198],"visual":[4,14,37,59,72,78,102,122,144,155,179,186,216],"input":[5],"equips":[6],"multimodal":[7],"large":[8],"language":[9],"models":[10],"(MLLMs)":[11],"with":[12,124,195,210],"enhanced":[13],"perception":[15],"capabilities":[16],"for":[17,135],"real-world":[18],"tasks.":[19],"However,":[20],"most":[21],"existing":[22],"MLLMs":[24],"rely":[25],"on":[26,197],"a":[27,40,57,89,98,119,125,159,201,211],"cropping-based":[28],"approach":[29],"to":[30,35,62,105,117],"process":[31],"images,":[32],"which":[33],"leads":[34],"fragmented":[36,154],"encoding":[38,150],"and":[39,169],"sharp":[41],"increase":[42],"in":[43,81,143,215],"redundant":[44,66],"tokens.":[45,217],"To":[46,74,146],"tackle":[47],"these":[48],"issues,":[49],"we":[50,87,157],"propose":[51,88],"the":[52,69,77,82,115,133,148,183,189],"FALCON":[53,55,196,206],"model.":[54],"introduces":[56,97],"novel":[58],"register":[60],"technique":[61],"simultaneously:":[63],"1)":[64],"Eliminate":[65],"tokens":[67],"at":[68],"stage":[70],"encoding.":[73,145,190],"directly":[75],"address":[76,147],"redundancy":[79],"present":[80],"output":[83,129],"vision":[85],"encoder,":[86],"Register-based":[90],"Representation":[91],"Compacting":[92],"(ReCompact)":[93],"mechanism.":[94],"This":[95,165],"mechanism":[96],"set":[99],"learnable":[101],"registers":[103],"designed":[104],"adaptively":[106],"aggregate":[107],"essential":[108],"information":[109,171],"while":[110],"discarding":[111],"redundancy.":[112],"It":[113,181],"enables":[114],"encoder":[116],"produce":[118],"more":[120],"compact":[121],"representation":[123],"minimal":[126],"number":[127],"tokens,":[130],"thus":[131],"eliminating":[132],"need":[134],"an":[136],"additional":[137],"compression":[138],"module.":[139,164],"2)":[140],"Ensure":[141],"continuity":[142,184],"potential":[149],"errors":[151],"caused":[152],"by":[153,175],"inputs,":[156],"develop":[158],"Register":[160],"Interactive":[161],"Attention":[162],"(ReAtten)":[163],"module":[166],"facilitates":[167],"effective":[168],"efficient":[170],"exchange":[172],"across":[173,200],"sub-images":[174],"enabling":[176],"interactions":[177],"between":[178],"registers.":[180],"ensures":[182],"semantics":[187],"throughout":[188],"We":[191],"conduct":[192],"comprehensive":[193],"experiments":[194],"benchmarks":[199],"wide":[202],"range":[203],"scenarios.":[205],"demonstrates":[207],"superior":[208],"performance":[209],"remarkable":[212],"9-fold":[213],"reduction":[214]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
