{"id":"https://openalex.org/W7138374988","doi":"https://doi.org/10.1609/aaai.v40i6.42450","title":"O3SLM: Open Weight, Open Data, and Open Vocabulary Sketch-Language Model","display_name":"O3SLM: Open Weight, Open Data, and Open Vocabulary Sketch-Language Model","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138374988","doi":"https://doi.org/10.1609/aaai.v40i6.42450"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i6.42450","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i6.42450","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i6.42450","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129727843","display_name":"Rishi Gupta","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rishi Gupta","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129693877","display_name":"Mukilan Karuppasamy","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mukilan Karuppasamy","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072834529","display_name":"Shyam Marjit","orcid":"https://orcid.org/0000-0002-7385-4432"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shyam Marjit","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019078651","display_name":"Aditay Tripathi","orcid":"https://orcid.org/0000-0002-1667-9623"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aditay Tripathi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5129705705","display_name":"Anirban Chakraborty","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anirban Chakraborty","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":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.63817664,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"6","first_page":"4511","last_page":"4519"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9894000291824341,"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":0.9894000291824341,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.0027000000700354576,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.0024999999441206455,"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/sketch","display_name":"Sketch","score":0.7354000210762024},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.6449000239372253},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6018999814987183},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.5863999724388123},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5573999881744385},{"id":"https://openalex.org/keywords/comprehension","display_name":"Comprehension","score":0.5209000110626221},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4880000054836273},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.4871000051498413}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8080999851226807},{"id":"https://openalex.org/C2779231336","wikidata":"https://www.wikidata.org/wiki/Q7534724","display_name":"Sketch","level":2,"score":0.7354000210762024},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6668000221252441},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.656000018119812},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.6449000239372253},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6018999814987183},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.5863999724388123},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5573999881744385},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.5209000110626221},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4880000054836273},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.4871000051498413},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.476500004529953},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.36809998750686646},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.3614000082015991},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.35920000076293945},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3562000095844269},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.35030001401901245},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.3458000123500824},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.33880001306533813},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.30309998989105225},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.2782999873161316},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.27090001106262207},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2639000117778778},{"id":"https://openalex.org/C2780103172","wikidata":"https://www.wikidata.org/wiki/Q1309721","display_name":"Visual Objects","level":3,"score":0.2597000002861023}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i6.42450","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i6.42450","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/42450","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/42450","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i6.42450","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i6.42450","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8759444355964661}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"While":[0],"Large":[1],"Vision":[2],"Language":[3],"Models":[4],"(LVLMs)":[5],"are":[6,39],"increasingly":[7],"deployed":[8],"in":[9,153],"real-world":[10],"applications,":[11],"their":[12],"ability":[13],"to":[14,24,41,84],"interpret":[15],"abstract":[16],"visual":[17,121],"inputs":[18],"remains":[19],"limited.":[20],"Specifically,":[21],"they":[22],"struggle":[23],"comprehend":[25],"hand-drawn":[26],"sketches,":[27,59],"a":[28,53,76],"modality":[29],"that":[30,38,56,144],"offers":[31],"an":[32,94],"intuitive":[33],"means":[34],"of":[35,52,80],"expressing":[36],"concepts":[37],"difficult":[40],"describe":[42],"textually.":[43],"We":[44],"identify":[45],"the":[46,50,127],"primary":[47],"bottleneck":[48],"as":[49],"absence":[51],"large-scale":[54,78],"dataset":[55,79],"jointly":[57],"models":[58],"photorealistic":[60],"images,":[61],"and":[62,88,91,116,119,135,156],"corresponding":[63],"natural":[64],"language":[65],"instructions.":[66],"To":[67],"address":[68],"this,":[69],"we":[70],"present":[71],"two":[72],"key":[73],"contributions:":[74],"(1)":[75],"new,":[77],"image-sketch-instruction":[81],"triplets":[82],"designed":[83],"facilitate":[85],"both":[86],"pretraining":[87],"instruction":[89],"tuning,":[90],"(2)":[92],"O3SLM,":[93],"LVLM":[95],"trained":[96],"on":[97,102],"this":[98],"dataset.":[99],"Comprehensive":[100],"evaluations":[101],"multiple":[103],"sketch-based":[104],"tasks:":[105],"(a)":[106],"object":[107],"localization,":[108],"(b)":[109],"counting,":[110],"(c)":[111],"image":[112],"retrieval":[113],"i.e.,":[114],"(SBIR":[115],"fine-grained":[117],"SBIR),":[118],"(d)":[120],"question":[122],"answering":[123],"(VQA);":[124],"while":[125],"incorporating":[126],"three":[128],"existing":[129,151],"sketch":[130,154],"datasets,":[131],"namely":[132],"QuickDraw!,":[133],"Sketchy,":[134],"Tu-Berlin,":[136],"along":[137],"with":[138],"our":[139],"generated":[140],"SketchVCL":[141],"dataset,":[142],"show":[143],"O3SLM":[145],"achieves":[146],"state-of-the-art":[147],"performance,":[148],"substantially":[149],"outperforming":[150],"LVLMs":[152],"comprehension":[155],"reasoning.":[157]},"counts_by_year":[],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2026-03-18T00:00:00"}