{"id":"https://openalex.org/W7134895240","doi":"https://doi.org/10.48550/arxiv.2603.09312","title":"IntroSVG: Learning from Rendering Feedback for Text-to-SVG Generation via an Introspective Generator-Critic Framework","display_name":"IntroSVG: Learning from Rendering Feedback for Text-to-SVG Generation via an Introspective Generator-Critic Framework","publication_year":2026,"publication_date":"2026-03-10","ids":{"openalex":"https://openalex.org/W7134895240","doi":"https://doi.org/10.48550/arxiv.2603.09312"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.09312","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.09312","pdf_url":null,"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.09312","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5128789073","display_name":"Feiyu Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Feiyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128756073","display_name":"Jiayuan Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Jiayuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128746910","display_name":"Zhiyuan Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Zhiyuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128797822","display_name":"Da Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Da","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128722957","display_name":"Bingyu Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Bingyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128719328","display_name":"Peng Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Peng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5128708865","display_name":"Junyu Gao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gao, Junyu","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":null,"has_fulltext":false,"cited_by_count":0,"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":0.722599983215332,"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":0.722599983215332,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.11590000241994858,"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/T10028","display_name":"Topic Modeling","score":0.016599999740719795,"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/leverage","display_name":"Leverage (statistics)","score":0.567300021648407},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.5669999718666077},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5656999945640564},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.5062000155448914},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.41260001063346863},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.3991999924182892},{"id":"https://openalex.org/keywords/scalable-vector-graphics","display_name":"Scalable Vector Graphics","score":0.3921999931335449},{"id":"https://openalex.org/keywords/iterative-and-incremental-development","display_name":"Iterative and incremental development","score":0.36419999599456787}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8317000269889832},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.567300021648407},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.5669999718666077},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5656999945640564},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5389999747276306},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.5062000155448914},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.41260001063346863},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.40549999475479126},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3991999924182892},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3950999975204468},{"id":"https://openalex.org/C202629362","wikidata":"https://www.wikidata.org/wiki/Q2078","display_name":"Scalable Vector Graphics","level":2,"score":0.3921999931335449},{"id":"https://openalex.org/C143587482","wikidata":"https://www.wikidata.org/wiki/Q1543216","display_name":"Iterative and incremental development","level":2,"score":0.36419999599456787},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.32519999146461487},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.31839999556541443},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.3077000081539154},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.30489999055862427},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.30309998989105225},{"id":"https://openalex.org/C77660652","wikidata":"https://www.wikidata.org/wiki/Q150971","display_name":"Computer graphics","level":2,"score":0.27230000495910645},{"id":"https://openalex.org/C2777868144","wikidata":"https://www.wikidata.org/wiki/Q7239817","display_name":"Preference elicitation","level":3,"score":0.27160000801086426},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.27090001106262207},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.26420000195503235},{"id":"https://openalex.org/C2776496909","wikidata":"https://www.wikidata.org/wiki/Q7313984","display_name":"Repertory grid","level":2,"score":0.26420000195503235},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.2615000009536743},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.2581000030040741}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.09312","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.09312","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.09312","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.09312","pdf_url":null,"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7126049995422363}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Scalable":[0],"Vector":[1],"Graphics":[2],"(SVG)":[3],"are":[4,32],"central":[5],"to":[6,10,100,104,133,168],"digital":[7],"design":[8],"due":[9],"their":[11,108],"inherent":[12],"scalability":[13],"and":[14,90,103,138,154,196],"editability.":[15,198],"Despite":[16],"significant":[17],"advancements":[18],"in":[19,80,158],"content":[20],"generation":[21,30,55,211],"enabled":[22],"by":[23,34],"Visual":[24],"Language":[25],"Models":[26],"(VLMs),":[27],"existing":[28],"text-to-SVG":[29],"methods":[31],"limited":[33],"a":[35,75,81,129,135],"core":[36],"challenge:":[37],"the":[38,48,72,97,141,151,202,210],"autoregressive":[39],"training":[40,120],"process":[41],"does":[42],"not":[43],"incorporate":[44],"visual":[45,207],"perception":[46],"of":[47,87,204],"final":[49],"rendered":[50,109],"image,":[51],"which":[52],"fundamentally":[53],"constrains":[54],"quality.":[56,172],"To":[57],"address":[58],"this":[59],"limitation,":[60],"we":[61,112,127],"propose":[62],"an":[63,159],"Introspective":[64],"SVG":[65],"Generation":[66],"Framework":[67],"(IntroSVG).":[68],"At":[69],"its":[70],"core,":[71],"framework":[73],"instantiates":[74],"unified":[76],"VLM":[77,132],"that":[78,176],"operates":[79],"closed":[82],"loop,":[83],"assuming":[84],"dual":[85],"roles":[86],"both":[88],"generator":[89,153],"critic.":[91],"Specifically,":[92],"through":[93,144],"Supervised":[94],"Fine-Tuning":[95],"(SFT),":[96],"model":[98,124],"learns":[99],"draft":[101],"SVGs":[102,188],"provide":[105],"feedback":[106,208],"on":[107],"outputs;":[110],"moreover,":[111],"systematically":[113],"convert":[114],"early-stage":[115],"failures":[116],"into":[117,209],"high-quality":[118],"error-correction":[119],"data,":[121],"thereby":[122],"enhancing":[123],"robustness.":[125],"Subsequently,":[126],"leverage":[128],"high-capacity":[130],"teacher":[131],"construct":[134],"preference":[136],"dataset":[137],"further":[139],"align":[140],"generator's":[142],"policy":[143],"Direct":[145],"Preference":[146],"Optimization":[147],"(DPO).":[148],"During":[149],"inference,":[150],"optimized":[152],"critic":[155],"operate":[156],"collaboratively":[157],"iterative":[160],"\"generate-review-refine\"":[161],"cycle,":[162],"starting":[163],"from":[164],"imperfect":[165],"intermediate":[166],"drafts":[167],"autonomously":[169],"improve":[170],"output":[171],"Experimental":[173],"results":[174,200],"demonstrate":[175],"our":[177],"method":[178],"achieves":[179],"state-of-the-art":[180],"performance":[181],"across":[182],"several":[183],"key":[184],"evaluation":[185],"metrics,":[186],"generating":[187],"with":[189],"more":[190],"complex":[191],"structures,":[192],"stronger":[193],"semantic":[194],"alignment,":[195],"greater":[197],"These":[199],"corroborate":[201],"effectiveness":[203],"incorporating":[205],"explicit":[206],"loop.":[212]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-03-12T00:00:00"}