{"id":"https://openalex.org/W4400647053","doi":"https://doi.org/10.1109/tmm.2024.3428317","title":"LMEye: An Interactive Perception Network for Large Language Models","display_name":"LMEye: An Interactive Perception Network for Large Language Models","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4400647053","doi":"https://doi.org/10.1109/tmm.2024.3428317"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2024.3428317","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2024.3428317","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5019703861","display_name":"Yunxin Li","orcid":"https://orcid.org/0000-0003-4819-2489"},"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":true,"raw_author_name":"Yunxin Li","raw_affiliation_strings":["Department of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083079672","display_name":"Baotian Hu","orcid":"https://orcid.org/0000-0001-7490-684X"},"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":"Baotian Hu","raw_affiliation_strings":["Department of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114910960","display_name":"Xinyu Chen","orcid":"https://orcid.org/0009-0005-9857-1614"},"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":"Xinyu Chen","raw_affiliation_strings":["Department of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017116858","display_name":"Lin Ma","orcid":"https://orcid.org/0000-0002-7331-6132"},"institutions":[{"id":"https://openalex.org/I4210087373","display_name":"Meizu (China)","ror":"https://ror.org/0067g4302","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210087373"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin Ma","raw_affiliation_strings":["Meituan, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Meituan, Beijing, China","institution_ids":["https://openalex.org/I4210087373"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100359961","display_name":"Yong Xu","orcid":"https://orcid.org/0000-0003-0530-2123"},"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":"Yong Xu","raw_affiliation_strings":["Department of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100402911","display_name":"Min Zhang","orcid":"https://orcid.org/0000-0002-3895-5510"},"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":"Min Zhang","raw_affiliation_strings":["Department of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5019703861"],"corresponding_institution_ids":["https://openalex.org/I204983213"],"apc_list":null,"apc_paid":null,"fwci":7.9929,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.97840938,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"26","issue":null,"first_page":"10952","last_page":"10964"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9803000092506409,"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":0.9803000092506409,"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/T10028","display_name":"Topic Modeling","score":0.9763000011444092,"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/computer-science","display_name":"Computer science","score":0.8874678611755371},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.5281044244766235},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.44733038544654846},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3945898115634918},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3540281653404236}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8874678611755371},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5281044244766235},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.44733038544654846},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3945898115634918},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3540281653404236},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2024.3428317","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2024.3428317","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.4099999964237213,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G412859668","display_name":null,"funder_award_id":"62376067","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":94,"referenced_works":["https://openalex.org/W1956340063","https://openalex.org/W2560730294","https://openalex.org/W2883891001","https://openalex.org/W2947312908","https://openalex.org/W2963115613","https://openalex.org/W3091588028","https://openalex.org/W3094502228","https://openalex.org/W3103668594","https://openalex.org/W3115819524","https://openalex.org/W3120867192","https://openalex.org/W3172048555","https://openalex.org/W3174770825","https://openalex.org/W3176896951","https://openalex.org/W4205385624","https://openalex.org/W4225650823","https://openalex.org/W4229005866","https://openalex.org/W4285294723","https://openalex.org/W4307079201","https://openalex.org/W4312651322","https://openalex.org/W4321177655","https://openalex.org/W4322718191","https://openalex.org/W4323717348","https://openalex.org/W4361229539","https://openalex.org/W4367367040","https://openalex.org/W4375869762","https://openalex.org/W4376122449","https://openalex.org/W4378464424","https://openalex.org/W4378711593","https://openalex.org/W4382491206","https://openalex.org/W4385245566","https://openalex.org/W4385571124","https://openalex.org/W4385572634","https://openalex.org/W4386071687","https://openalex.org/W4387356416","https://openalex.org/W4388685724","https://openalex.org/W4391376671","https://openalex.org/W4391377114","https://openalex.org/W4391590851","https://openalex.org/W4391631722","https://openalex.org/W4400647053","https://openalex.org/W4402716330","https://openalex.org/W4402753980","https://openalex.org/W4403002096","https://openalex.org/W4403081466","https://openalex.org/W4404594861","https://openalex.org/W6678262379","https://openalex.org/W6682631176","https://openalex.org/W6755946662","https://openalex.org/W6757817989","https://openalex.org/W6791353385","https://openalex.org/W6796581206","https://openalex.org/W6809646742","https://openalex.org/W6810334672","https://openalex.org/W6810738896","https://openalex.org/W6811340617","https://openalex.org/W6839015040","https://openalex.org/W6845514976","https://openalex.org/W6845965238","https://openalex.org/W6847076894","https://openalex.org/W6847903763","https://openalex.org/W6849177959","https://openalex.org/W6849732303","https://openalex.org/W6849898756","https://openalex.org/W6850015000","https://openalex.org/W6850071225","https://openalex.org/W6850503672","https://openalex.org/W6850625674","https://openalex.org/W6851592950","https://openalex.org/W6851813333","https://openalex.org/W6851904846","https://openalex.org/W6851948999","https://openalex.org/W6851950068","https://openalex.org/W6852060543","https://openalex.org/W6852123154","https://openalex.org/W6852365775","https://openalex.org/W6852410717","https://openalex.org/W6852447913","https://openalex.org/W6852489829","https://openalex.org/W6852512478","https://openalex.org/W6852667213","https://openalex.org/W6852755768","https://openalex.org/W6853116092","https://openalex.org/W6853122427","https://openalex.org/W6854262950","https://openalex.org/W6854510102","https://openalex.org/W6856391844","https://openalex.org/W6856559388","https://openalex.org/W6858379761","https://openalex.org/W6858826905","https://openalex.org/W6861291810","https://openalex.org/W6861475616","https://openalex.org/W6861503643","https://openalex.org/W6861737562","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Current":[0],"efficient":[1],"approaches":[2],"to":[3,64,72,79,102,117,144,177,185,194,232],"building":[4],"Multimodal":[5],"Large":[6],"Language":[7],"Models":[8],"(MLLMs)":[9],"mainly":[10],"incorporate":[11],"visual":[12,19,59,82,110,121,132,141,167,175,197],"information":[13,60,122,133,168,176,198],"into":[14],"LLMs":[15,71,107,183],"with":[16,95,124,235],"a":[17,24,28,92,96,139],"simple":[18,140],"mapping":[20,142],"network":[21,143],"such":[22],"as":[23,80],"linear":[25],"projection":[26],"layer,":[27],"multilayer":[29],"perceptron":[30],"(MLP),":[31],"or":[32],"Q-former":[33],"from":[34,163],"BLIP-2.":[35],"Such":[36],"networks":[37],"project":[38],"the":[39,47,50,53,57,115,119,146,172,187,191,195,203,207],"image":[40,51,151],"feature":[41],"once":[42],"and":[43,52,108,170,201,244,250],"do":[44],"not":[45],"consider":[46],"interaction":[48,105,199],"between":[49,106],"human":[54,65,126,188],"inputs.":[55],"Hence,":[56],"obtained":[58],"without":[61],"being":[62],"connected":[63],"intention":[66],"may":[67],"be":[68],"inadequate":[69],"for":[70,152,160],"generate":[73,202],"intention-following":[74],"responses,":[75],"which":[76,128],"we":[77,129,239],"refer":[78],"static":[81],"information.":[83,111,210],"To":[84],"alleviate":[85],"this":[86,181],"issue,":[87],"our":[88],"paper":[89],"introduces":[90],"LMEye,":[91],"human-like":[93],"eye":[94],"play-and-plug":[97],"interactive":[98],"perception":[99,148],"network,":[100],"designed":[101],"enable":[103],"dynamic":[104,131],"external":[109],"It":[112,154],"can":[113],"allow":[114],"LLM":[116],"request":[118,193],"desired":[120],"aligned":[123],"various":[125,228,247],"instructions,":[127],"term":[130],"acquisition.":[134],"Specifically,":[135],"LMEye":[136,213],"consists":[137],"of":[138,149],"provide":[145],"basic":[147],"an":[150],"LLMs.":[153],"also":[155,240],"contains":[156],"additional":[157],"modules":[158],"responsible":[159],"acquiring":[161],"requests":[162],"LLMs,":[164,178],"performing":[165],"request-based":[166,196],"seeking,":[169],"transmitting":[171],"resulting":[173],"interacted":[174],"respectively.":[179,253],"In":[180],"way,":[182],"act":[184],"understand":[186],"query,":[189],"deliver":[190],"corresponding":[192],"module,":[200],"response":[204],"based":[205],"on":[206,217,227,246],"interleaved":[208],"multimodal":[209,218,229],"We":[211],"evaluate":[212],"through":[214],"extensive":[215],"experiments":[216],"benchmarks,":[219],"demonstrating":[220],"that":[221],"it":[222],"significantly":[223],"improves":[224],"zero-shot":[225],"performances":[226],"tasks":[230],"compared":[231],"previous":[233],"methods,":[234],"fewer":[236],"parameters.":[237],"Moreover,":[238],"verify":[241],"its":[242],"effectiveness":[243],"scalability":[245],"language":[248],"models":[249],"video":[251],"understanding,":[252]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":16},{"year":2024,"cited_by_count":5}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}