{"id":"https://openalex.org/W7166817265","doi":"https://doi.org/10.18653/v1/2026.findings-acl.365","title":"VizoMem: A Visual-Textual Memory Framework for Efficient Long-Horizon Reasoning","display_name":"VizoMem: A Visual-Textual Memory Framework for Efficient Long-Horizon Reasoning","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166817265","doi":"https://doi.org/10.18653/v1/2026.findings-acl.365"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.365","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.365","pdf_url":"https://aclanthology.org/2026.findings-acl.365.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-acl.365.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139763175","display_name":"Weijie Liang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weijie Liang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139839097","display_name":"Yuanfeng Song","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuanfeng Song","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139767117","display_name":"Xing Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xing Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052597827","display_name":"Caleb Chen Cao","orcid":"https://orcid.org/0000-0002-8050-2486"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Caleb Chen Cao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139834956","display_name":"Sirui Han","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sirui Han","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139806936","display_name":"Yike Guo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yike Guo","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":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.86209744,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7399","last_page":"7422"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.7850000262260437,"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":0.7850000262260437,"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/T11596","display_name":"Constraint Satisfaction and Optimization","score":0.04129999876022339,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.017100000753998756,"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/automated-reasoning","display_name":"Automated reasoning","score":0.3043999969959259},{"id":"https://openalex.org/keywords/non-monotonic-logic","display_name":"Non-monotonic logic","score":0.29989999532699585},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.27869999408721924},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.25459998846054077},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.24330000579357147}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6524999737739563},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4602000117301941},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.3043999969959259},{"id":"https://openalex.org/C159032336","wikidata":"https://www.wikidata.org/wiki/Q2488768","display_name":"Non-monotonic logic","level":2,"score":0.29989999532699585},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.27869999408721924},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.25459998846054077},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.24490000307559967},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.24330000579357147},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.23849999904632568},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.23330000042915344}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.365","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.365","pdf_url":"https://aclanthology.org/2026.findings-acl.365.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.365","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.365","pdf_url":"https://aclanthology.org/2026.findings-acl.365.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1142957533","display_name":null,"funder_award_id":"R9911","funder_id":"https://openalex.org/F4320323537","funder_display_name":"Hong Kong University of Science and Technology"},{"id":"https://openalex.org/G7049909837","display_name":null,"funder_award_id":"T45-205/21-N","funder_id":"https://openalex.org/F4320323537","funder_display_name":"Hong Kong University of Science and Technology"}],"funders":[{"id":"https://openalex.org/F4320321920","display_name":"Innovation and Technology Commission","ror":"https://ror.org/04vf9tr09"},{"id":"https://openalex.org/F4320323537","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166817265.pdf","grobid_xml":"https://content.openalex.org/works/W7166817265.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Agentic":[0],"systems":[1],"built":[2],"upon":[3],"large":[4],"language":[5],"models":[6,97],"(LLMs)":[7],"increasingly":[8],"depend":[9],"on":[10,140],"longcontext":[11],"modeling":[12],"to":[13,134,164],"support":[14],"document":[15],"understanding,":[16],"long-term":[17,154],"memory":[18,30,69,92,155],"recall,":[19,156],"and":[20,29,36,55,83,90,120],"multi-step":[21],"reasoning.However,":[22],"extending":[23],"context":[24],"windows":[25],"incurs":[26],"substantial":[27],"computational":[28],"overhead,":[31],"significantly":[32,147],"limiting":[33],"the":[34,114,121],"scalability":[35],"practicality":[37],"of":[38,116,123],"long-context":[39,166],"LLM-based":[40],"agents.Recent":[41],"studies":[42],"suggest":[43],"that":[44,129,144],"visual":[45,68,86,109,138],"representations":[46],"can":[47],"serve":[48],"as":[49,85,160],"an":[50],"effective":[51,153],"medium":[52],"for":[53,71,107],"compressing":[54],"organizing":[56],"long":[57],"textual":[58,76],"content.Motivated":[59],"by":[60],"this":[61,74],"insight,":[62],"we":[63,100],"propose":[64],"VizoMem,":[65],"a":[66,102,117,124,161],"novel":[67],"framework":[70],"agentic":[72],"systems.In":[73],"framework,":[75],"memories":[77],"are":[78],"pre-rendered":[79],"into":[80],"structured":[81],"images":[82],"stored":[84],"notes,":[87],"enabling":[88],"compact":[89],"persistent":[91],"representations.Moving":[93],"beyond":[94],"standard":[95],"visionlanguage":[96],"like":[98],"Glyph,":[99],"pioneer":[101],"specialized":[103],"retrieval":[104,127],"system":[105],"designed":[106],"largescale":[108],"memory.Our":[110],"innovation":[111],"lies":[112],"in":[113],"construction":[115],"dedicated":[118],"dataset":[119],"development":[122],"highly":[125],"efficient":[126],"model":[128],"repurposes":[130],"foundational":[131],"vision-language":[132],"encoders":[133],"navigate":[135],"complex,":[136],"text-heavy":[137],"environments.Experiments":[139],"public":[141],"datasets":[142],"demonstrate":[143],"our":[145],"approach":[146],"reduces":[148],"token":[149],"consumption":[150],"while":[151],"preserving":[152],"highlighting":[157],"its":[158],"potential":[159],"scalable":[162],"alternative":[163],"conventional":[165],"modeling.":[167]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}