{"id":"https://openalex.org/W7208741194","doi":"https://doi.org/10.48550/arxiv.2609.04131","title":"Beyond Retrieval: Progressive Latent Memory Evolution for Streaming Video Understanding","display_name":"Beyond Retrieval: Progressive Latent Memory Evolution for Streaming Video Understanding","publication_year":2026,"publication_date":"2026-09-03","ids":{"openalex":"https://openalex.org/W7208741194","doi":"https://doi.org/10.48550/arxiv.2609.04131"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.04131","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.04131","pdf_url":"https://arxiv.org/pdf/2609.04131","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":"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/2609.04131","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5122790017","display_name":"Hongyu Qu","orcid":"https://orcid.org/0009-0001-5064-4993","observed_orcids":["https://orcid.org/0009-0001-5064-4993"]},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qu, Hongyu","raw_affiliation_strings":["Nanjing University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University of Science and Technology","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082771951","display_name":"Guangming Yao","orcid":"https://orcid.org/0000-0002-4819-0101","observed_orcids":["https://orcid.org/0000-0002-4819-0101"]},"institutions":[{"id":"https://openalex.org/I4405270328","display_name":"Ant Group (China)","ror":"https://ror.org/00g5w7n47","country_code":"CN","type":"company","lineage":["https://openalex.org/I4405270328"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yao, Guangming","raw_affiliation_strings":["Ant Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ant Group","institution_ids":["https://openalex.org/I4405270328"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100727912","display_name":"Ling Xing","orcid":"https://orcid.org/0009-0001-6943-462X","observed_orcids":["https://orcid.org/0009-0001-6943-462X"]},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xing, Ling","raw_affiliation_strings":["Nanjing University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University of Science and Technology","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122979899","display_name":"Xiaobin Hu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Hu, Xiaobin","raw_affiliation_strings":["National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5150037741","display_name":"Rongxing Ding","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ding, Rongxing","raw_affiliation_strings":["Nanjing University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University of Science and Technology","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132839483","display_name":"Guibin Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Zhang, Guibin","raw_affiliation_strings":["National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5150036874","display_name":"Fan Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Zhang, Fan","raw_affiliation_strings":["The Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138226816","display_name":"Yi Yuan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405270328","display_name":"Ant Group (China)","ror":"https://ror.org/00g5w7n47","country_code":"CN","type":"company","lineage":["https://openalex.org/I4405270328"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuan, Yi","raw_affiliation_strings":["Ant Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ant Group","institution_ids":["https://openalex.org/I4405270328"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040437528","display_name":"Xiangbo Shu","orcid":"https://orcid.org/0000-0003-4902-4663","observed_orcids":["https://orcid.org/0000-0003-4902-4663"]},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shu, Xiangbo","raw_affiliation_strings":["Nanjing University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University of Science and Technology","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5121616404","display_name":"Shuicheng Yan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yan, Shuicheng","raw_affiliation_strings":["National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"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/T11605","display_name":"Visual Attention and Saliency Detection","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"}},{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","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/latent-memory","display_name":"latent memory","score":0.6690000295639038},{"id":"https://openalex.org/keywords/multimodal-large-language-models","display_name":"multimodal large language models","score":0.9120000004768372},{"id":"https://openalex.org/keywords/memory-bank","display_name":"memory bank","score":0.30300000309944153},{"id":"https://openalex.org/keywords/hierarchical-memory","display_name":"hierarchical memory","score":0.4779999852180481},{"id":"https://openalex.org/keywords/memory-consolidation","display_name":"memory consolidation","score":0.6010000109672546},{"id":"https://openalex.org/keywords/predictive-entropy","display_name":"predictive entropy","score":0.5789999961853027}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8235999941825867},{"id":"https://openalex.org/C2777611316","wikidata":"https://www.wikidata.org/wiki/Q39045282","display_name":"Streaming data","level":2,"score":0.5537999868392944},{"id":"https://openalex.org/C30390489","wikidata":"https://www.wikidata.org/wiki/Q4680748","display_name":"Adaptive memory","level":3,"score":0.5440999865531921},{"id":"https://openalex.org/C58632812","wikidata":"https://www.wikidata.org/wiki/Q7936625","display_name":"Visual short-term memory","level":4,"score":0.4115999937057495},{"id":"https://openalex.org/C57863822","wikidata":"https://www.wikidata.org/wiki/Q905488","display_name":"Flat memory model","level":4,"score":0.3822999894618988},{"id":"https://openalex.org/C178278151","wikidata":"https://www.wikidata.org/wiki/Q7936607","display_name":"Visual memory","level":3,"score":0.3815999925136566},{"id":"https://openalex.org/C21963081","wikidata":"https://www.wikidata.org/wiki/Q11337567","display_name":"Working memory","level":3,"score":0.373199999332428},{"id":"https://openalex.org/C74426580","wikidata":"https://www.wikidata.org/wiki/Q719484","display_name":"Memory map","level":3,"score":0.3573000133037567},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3555000126361847},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.34869998693466187},{"id":"https://openalex.org/C82687282","wikidata":"https://www.wikidata.org/wiki/Q66221","display_name":"Auxiliary memory","level":2,"score":0.3352000117301941},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.3215999901294708},{"id":"https://openalex.org/C179226034","wikidata":"https://www.wikidata.org/wiki/Q18599","display_name":"Short-term memory","level":4,"score":0.30480000376701355},{"id":"https://openalex.org/C63511323","wikidata":"https://www.wikidata.org/wiki/Q908936","display_name":"Interleaved memory","level":4,"score":0.2985999882221222},{"id":"https://openalex.org/C88576662","wikidata":"https://www.wikidata.org/wiki/Q18646","display_name":"Episodic memory","level":3,"score":0.2930999994277954},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.289900004863739},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.2858000099658966},{"id":"https://openalex.org/C12186640","wikidata":"https://www.wikidata.org/wiki/Q6815743","display_name":"Memory model","level":3,"score":0.27559998631477356},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2750000059604645},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2623000144958496},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2572000026702881},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.2549999952316284},{"id":"https://openalex.org/C64357122","wikidata":"https://www.wikidata.org/wiki/Q1149766","display_name":"Causality (physics)","level":2,"score":0.25429999828338623},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.2538999915122986}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.04131","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.04131","pdf_url":"https://arxiv.org/pdf/2609.04131","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2609.04131","doi":"https://doi.org/10.48550/arxiv.2609.04131","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.04131","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:2609.04131","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.04131","pdf_url":"https://arxiv.org/pdf/2609.04131","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7208741194.pdf","grobid_xml":"https://content.openalex.org/works/W7208741194.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W4392679398","https://openalex.org/W4403370767","https://openalex.org/W4403853618","https://openalex.org/W4404304985","https://openalex.org/W4404330874","https://openalex.org/W4407794264","https://openalex.org/W4415328697","https://openalex.org/W4416051564","https://openalex.org/W4416452771","https://openalex.org/W6929474479","https://openalex.org/W7133361182","https://openalex.org/W7133536881","https://openalex.org/W7133866787","https://openalex.org/W7135196770","https://openalex.org/W7136697772","https://openalex.org/W7138091585","https://openalex.org/W7140100370","https://openalex.org/W7147613864","https://openalex.org/W7148741700","https://openalex.org/W7155093650","https://openalex.org/W7160259280","https://openalex.org/W7160856542","https://openalex.org/W7166493911","https://openalex.org/W7167629185"],"related_works":["https://openalex.org/W7202258175","https://openalex.org/W7164927711","https://openalex.org/W7171946046","https://openalex.org/W7215130093","https://openalex.org/W7127301285","https://openalex.org/W7204763630","https://openalex.org/W7222450218","https://openalex.org/W7165892338","https://openalex.org/W7160856542","https://openalex.org/W7214934479"],"abstract_inverted_index":{"Streaming":[0,103],"video":[1,207],"understanding":[2],"requires":[3],"multimodal":[4],"large":[5],"language":[6],"models":[7],"(MLLMs)":[8],"to":[9,16,92,145],"process":[10],"continuous":[11],"visual":[12,42,54,106],"inputs":[13],"and":[14,22,36,111,154,178,185,205],"respond":[15],"user":[17],"queries":[18],"under":[19,114],"strict":[20],"causality":[21],"bounded":[23],"memory.":[24,162],"Existing":[25],"approaches":[26],"typically":[27],"compress":[28],"historical":[29,50,148],"observations":[30],"into":[31,61,108,157],"an":[32],"external":[33,53],"memory":[34,66,84,89,117,135,140,183],"bank":[35],"retrieve":[37,147],"query-relevant":[38],"evidence":[39,51,149],"as":[40,52],"additional":[41],"context.":[43],"Though":[44],"effective,":[45],"this":[46,75],"store-and-retrieve":[47,91],"paradigm":[48],"keeps":[49],"context,":[55],"preventing":[56],"it":[57,156],"from":[58,90,150,174],"being":[59],"internalized":[60],"a":[62,80,115,124,158,170],"compact,":[63,159],"evolving":[64],"latent":[65,82,134,161,182],"that":[67,86,196],"can":[68],"continuously":[69],"guide":[70],"streaming":[71,88,191],"reasoning.":[72,192],"To":[73],"bridge":[74],"gap,":[76],"we":[77],"introduce":[78],"LatentStream,":[79],"progressive":[81],"working":[83],"framework":[85],"shifts":[87],"retrieve-and-internalize.":[93],"Specifically,":[94],"LatentStream":[95,197],"comprises":[96],"three":[97],"coordinated":[98],"components.":[99],"First,":[100],"Query-agnostic":[101],"Hierarchical":[102,127],"Memory":[104,129,167],"organizes":[105],"history":[107],"short-,":[109],"mid-,":[110],"long-term":[112],"levels":[113],"fixed":[116],"budget":[118],"through":[119],"Jenks-guided":[120],"adaptive":[121],"consolidation.":[122],"Once":[123],"query":[125],"arrives,":[126],"Latent":[128,166],"Evolution":[130],"equips":[131],"groups":[132],"of":[133],"tokens":[136,184],"with":[137],"progressively":[138],"expanding":[139],"receptive":[141],"fields,":[142],"enabling":[143],"them":[144],"iteratively":[146],"their":[151],"corresponding":[152],"scopes":[153],"internalize":[155],"fixed-length":[160],"Finally,":[163],"Progressive":[164],"Confidence-guided":[165],"Optimization":[168],"constructs":[169],"hierarchical":[171],"progression":[172],"reward":[173],"group-wise":[175],"predictive":[176],"entropy":[177],"jointly":[179],"refines":[180],"the":[181],"retrieved":[186],"evidence,":[187],"encouraging":[188],"increasingly":[189],"confident":[190],"Extensive":[193],"experiments":[194],"demonstrate":[195],"achieves":[198],"new":[199],"state-of-the-art":[200],"results":[201],"on":[202],"existing":[203],"online":[204],"offline":[206],"benchmarks.":[208]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-09-05T00:00:00"}
