{"id":"https://openalex.org/W7167918601","doi":"https://doi.org/10.1145/3805712.3808383","title":"Visual RAG at Scale: Tile-Level Spatial Pooling for Efficient Multi-Vector Document Retrieval","display_name":"Visual RAG at Scale: Tile-Level Spatial Pooling for Efficient Multi-Vector Document Retrieval","publication_year":2026,"publication_date":"2026-07-10","ids":{"openalex":"https://openalex.org/W7167918601","doi":"https://doi.org/10.1145/3805712.3808383"},"language":null,"primary_location":{"id":"doi:10.1145/3805712.3808383","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3808383","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3805712.3808383","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5099038724","display_name":"Ara Yeroyan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210124008","display_name":"National Statistical Service of the Republic of Armenia","ror":"https://ror.org/037g7hc89","country_code":"AM","type":"other","lineage":["https://openalex.org/I4210124008"]}],"countries":["AM"],"is_corresponding":true,"raw_author_name":"Ara Yeroyan","raw_affiliation_strings":["ServiceTitan, Yerevan, Armenia"],"raw_orcid":"https://orcid.org/0009-0009-3605-9702","affiliations":[{"raw_affiliation_string":"ServiceTitan, Yerevan, Armenia","institution_ids":["https://openalex.org/I4210124008"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5099038724"],"corresponding_institution_ids":["https://openalex.org/I4210124008"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.93159805,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5245","last_page":"5249"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.5325000286102295,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.5325000286102295,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.29899999499320984,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.05169999971985817,"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/pooling","display_name":"Pooling","score":0.8300999999046326},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.7501999735832214},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.5055000185966492},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.42419999837875366},{"id":"https://openalex.org/keywords/visual-search","display_name":"Visual search","score":0.41620001196861267},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4027000069618225},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38269999623298645},{"id":"https://openalex.org/keywords/spatial-analysis","display_name":"Spatial analysis","score":0.3630000054836273}],"concepts":[{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.8300999999046326},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7605999708175659},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.7501999735832214},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5181999802589417},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.5055000185966492},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.45989999175071716},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.42419999837875366},{"id":"https://openalex.org/C158495155","wikidata":"https://www.wikidata.org/wiki/Q2369151","display_name":"Visual search","level":2,"score":0.41620001196861267},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4027000069618225},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38269999623298645},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.3630000054836273},{"id":"https://openalex.org/C189391414","wikidata":"https://www.wikidata.org/wiki/Q7936579","display_name":"Visual Word","level":4,"score":0.3434000015258789},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.33889999985694885},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.33469998836517334},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.304500013589859},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.29339998960494995},{"id":"https://openalex.org/C160086991","wikidata":"https://www.wikidata.org/wiki/Q5939193","display_name":"Human visual system model","level":3,"score":0.28610000014305115},{"id":"https://openalex.org/C130590232","wikidata":"https://www.wikidata.org/wiki/Q1671754","display_name":"Inverted index","level":3,"score":0.2671999931335449},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.26570001244544983},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2508000135421753},{"id":"https://openalex.org/C9770341","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Geospatial analysis","level":2,"score":0.25040000677108765}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3805712.3808383","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3808383","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3805712.3808383","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3808383","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":2,"referenced_works":["https://openalex.org/W3021397474","https://openalex.org/W7133214597"],"related_works":[],"abstract_inverted_index":{"Multi-vector":[0],"visual":[1,37],"retrievers":[2],"(e.g.,":[3],"ColPali-style":[4],"late":[5],"interaction":[6],"models)":[7],"deliver":[8],"strong":[9],"accuracy,":[10],"but":[11],"scale":[12],"poorly":[13],"because":[14],"each":[15],"page":[16],"yields":[17],"thousands":[18],"of":[19],"vectors,":[20],"making":[21],"indexing":[22],"and":[23,44,68],"search":[24],"increasingly":[25],"expensive.":[26],"We":[27],"present":[28],"Visual":[29],"RAG":[30],"Toolkit,":[31],"a":[32,57],"practical":[33],"system":[34],"for":[35,71],"scaling":[36],"multi-vector":[38,82],"retrieval":[39],"with":[40],"training-free,":[41],"model-aware":[42],"pooling":[43],"multi-stage":[45],"retrieval.":[46],"Motivated":[47],"by":[48,76],"Matryoshka":[49],"Embeddings,":[50],"our":[51],"method":[52],"performs":[53],"static":[54],"spatial":[55],"pooling--including":[56],"lightweight":[58],"sliding-window":[59],"averaging":[60],"variant--over":[61],"patch":[62],"embeddings":[63],"to":[64],"produce":[65],"compact":[66],"tile-level":[67],"global":[69],"representations":[70],"fast":[72],"candidate":[73],"generation,":[74],"followed":[75],"exact":[77],"MaxSim":[78],"reranking":[79],"using":[80],"full":[81],"embeddings.":[83]},"counts_by_year":[],"updated_date":"2026-07-11T05:49:48.208612","created_date":"2026-07-11T00:00:00"}