{"id":"https://openalex.org/W4415539558","doi":"https://doi.org/10.1145/3746027.3755392","title":"SVGThinker: Instruction-Aligned and Reasoning-Driven Text-to-SVG Generation","display_name":"SVGThinker: Instruction-Aligned and Reasoning-Driven Text-to-SVG Generation","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415539558","doi":"https://doi.org/10.1145/3746027.3755392"},"language":"en","primary_location":{"id":"doi:10.1145/3746027.3755392","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755392","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2509.24299","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5092949548","display_name":"Hanqi Chen","orcid":"https://orcid.org/0009-0005-5531-0182"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hanqi Chen","raw_affiliation_strings":["SJTU Paris Elite Institute of Technology, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0005-5531-0182","affiliations":[{"raw_affiliation_string":"SJTU Paris Elite Institute of Technology, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043235722","display_name":"Zhongyin Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongyin Zhao","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0000-2676-1412","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100359144","display_name":"Ye Chen","orcid":"https://orcid.org/0009-0002-4011-593X"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ye Chen","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0002-4011-593X","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120132119","display_name":"Zhujin Liang","orcid":"https://orcid.org/0000-0002-1278-5226"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhujin Liang","raw_affiliation_strings":["PhiGent Robotics, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-1278-5226","affiliations":[{"raw_affiliation_string":"PhiGent Robotics, Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102795444","display_name":"Bingbing Ni","orcid":"https://orcid.org/0000-0001-5582-577X"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bingbing Ni","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-5582-577X","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"11004","last_page":"11012"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9995999932289124,"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/T12031","display_name":"Speech and dialogue systems","score":0.9873999953269958,"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/scalable-vector-graphics","display_name":"Scalable Vector Graphics","score":0.9948999881744385},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.5921000242233276},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.5636000037193298},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5001000165939331},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.46709999442100525},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.43140000104904175},{"id":"https://openalex.org/keywords/code-generation","display_name":"Code generation","score":0.40130001306533813},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.3806999921798706}],"concepts":[{"id":"https://openalex.org/C202629362","wikidata":"https://www.wikidata.org/wiki/Q2078","display_name":"Scalable Vector Graphics","level":2,"score":0.9948999881744385},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7509999871253967},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.5921000242233276},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.5636000037193298},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5001000165939331},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.46709999442100525},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.43140000104904175},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.41659998893737793},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.40130001306533813},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39480000734329224},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3806999921798706},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3763999938964844},{"id":"https://openalex.org/C59662460","wikidata":"https://www.wikidata.org/wiki/Q170130","display_name":"Vector graphics","level":3,"score":0.3668999969959259},{"id":"https://openalex.org/C172367668","wikidata":"https://www.wikidata.org/wiki/Q6504956","display_name":"Data visualization","level":3,"score":0.3621000051498413},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3118000030517578},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.29670000076293945},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.28189998865127563},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.2816999852657318},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.26269999146461487},{"id":"https://openalex.org/C150292731","wikidata":"https://www.wikidata.org/wiki/Q1342704","display_name":"Code review","level":5,"score":0.26030001044273376},{"id":"https://openalex.org/C77660652","wikidata":"https://www.wikidata.org/wiki/Q150971","display_name":"Computer graphics","level":2,"score":0.250900000333786}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3746027.3755392","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755392","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2509.24299","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.24299","pdf_url":"https://arxiv.org/pdf/2509.24299","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2509.24299","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.24299","pdf_url":"https://arxiv.org/pdf/2509.24299","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":[],"awards":[{"id":"https://openalex.org/G546939068","display_name":null,"funder_award_id":"25ZR1401187","funder_id":"https://openalex.org/F4320321885","funder_display_name":"Science and Technology Commission of Shanghai Municipality"}],"funders":[{"id":"https://openalex.org/F4320321885","display_name":"Science and Technology Commission of Shanghai Municipality","ror":"https://ror.org/03kt66j61"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W2183341477","https://openalex.org/W2966583823","https://openalex.org/W4312933868","https://openalex.org/W4389335076"],"related_works":[],"abstract_inverted_index":{"Scalable":[0],"Vector":[1],"Graphics":[2],"(SVG)":[3],"is":[4],"a":[5,48,62,90,111],"code":[6,71],"structure":[7],"used":[8],"to":[9,39,65,93,102,154],"represent":[10],"visual":[11],"information,":[12],"and":[13,34,124,148,165,187],"with":[14,36,72,134,180],"the":[15,67,73,95,103,121,126,160],"powerful":[16],"capabilities":[17,33],"of":[18,69,84,106,128,163],"large":[19,55],"language":[20,56],"models,":[21,57,137],"it":[22],"holds":[23],"significant":[24],"research":[25],"potential.":[26],"Current":[27],"text-to-SVG":[28],"generation":[29,41,68],"methods":[30],"lack":[31],"generalization":[32],"struggle":[35],"accurately":[37],"adhering":[38],"input":[40],"instructions.":[42],"In":[43,152],"this":[44],"paper,":[45],"we":[46,87],"propose":[47],"novel":[49],"approach":[50,158],"for":[51,177],"generating":[52],"SVG":[53,70,79,85,150,164,178],"using":[54],"named":[58],"SVGThinker,":[59],"which":[60,119],"incorporates":[61],"reasoning":[63],"process":[64],"align":[66],"visualization":[74],"process,":[75],"while":[76],"supporting":[77],"all":[78],"primitives.":[80,107],"Through":[81,132],"sequential":[82,99],"rendering":[83],"primitives,":[86],"first":[88],"use":[89],"multimodal":[91],"model":[92,143],"annotate":[94],"SVG,":[96],"followed":[97],"by":[98],"updates":[100],"corresponding":[101],"incremental":[104],"additions":[105],"We":[108,170],"then":[109],"employ":[110],"supervised":[112],"training":[113],"framework":[114],"based":[115],"on":[116],"Chain-of-Thought":[117],"reasoning,":[118],"enhances":[120],"model's":[122],"robustness":[123],"reduces":[125],"risk":[127],"errors":[129],"or":[130],"hallucinations.":[131],"comparisons":[133],"state-of-the-art":[135],"baseline":[136],"our":[138,142,157,172],"experiments":[139],"show":[140],"that":[141],"generates":[144],"more":[145],"stable,":[146],"high-quality,":[147],"editable":[149],"code.":[151],"contrast":[153],"image-based":[155],"methods,":[156],"preserves":[159],"structural":[161],"advantages":[162],"supports":[166],"precise,":[167],"hierarchical":[168],"editing.":[169],"believe":[171],"work":[173],"opens":[174],"new":[175],"directions":[176],"generation,":[179],"potential":[181],"applications":[182],"in":[183],"design,":[184],"content":[185],"creation,":[186],"automated":[188],"SVG-based":[189],"graphic":[190],"generation.":[191]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-25T00:00:00"}
