{"id":"https://openalex.org/W7155395127","doi":"https://doi.org/10.48550/arxiv.2604.20730","title":"Render-in-the-Loop: Vector Graphics Generation via Visual Self-Feedback","display_name":"Render-in-the-Loop: Vector Graphics Generation via Visual Self-Feedback","publication_year":2026,"publication_date":"2026-04-22","ids":{"openalex":"https://openalex.org/W7155395127","doi":"https://doi.org/10.48550/arxiv.2604.20730"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.20730","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.20730","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.2604.20730","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113395536","display_name":"Guotao Liang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liang, Guotao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134422115","display_name":"Zhangcheng Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Zhangcheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134437227","display_name":"Juncheng Hu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hu, Juncheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101586543","display_name":"Haitao Zhou","orcid":"https://orcid.org/0000-0002-6809-6366"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Haitao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113145361","display_name":"Ziteng Xue","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xue, Ziteng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134454556","display_name":"Jing Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Jing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134457100","display_name":"Dong Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Dong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5134455415","display_name":"Qian Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Qian","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":0.5701000094413757,"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":0.5701000094413757,"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":0.21060000360012054,"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/T10799","display_name":"Data Visualization and Analytics","score":0.03709999844431877,"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/rendering","display_name":"Rendering (computer graphics)","score":0.5552999973297119},{"id":"https://openalex.org/keywords/scalable-vector-graphics","display_name":"Scalable Vector Graphics","score":0.5515999794006348},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.4449000060558319},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.42399999499320984},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.4000000059604645},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.3763999938964844},{"id":"https://openalex.org/keywords/visual-language","display_name":"Visual language","score":0.3562000095844269},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.34200000762939453},{"id":"https://openalex.org/keywords/human-visual-system-model","display_name":"Human visual system model","score":0.3391999900341034}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7752000093460083},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.5552999973297119},{"id":"https://openalex.org/C202629362","wikidata":"https://www.wikidata.org/wiki/Q2078","display_name":"Scalable Vector Graphics","level":2,"score":0.5515999794006348},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5343000292778015},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.4449000060558319},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.42399999499320984},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4000000059604645},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3763999938964844},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3562999963760376},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.3562000095844269},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.34200000762939453},{"id":"https://openalex.org/C160086991","wikidata":"https://www.wikidata.org/wiki/Q5939193","display_name":"Human visual system model","level":3,"score":0.3391999900341034},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.33149999380111694},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.32739999890327454},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.3149000108242035},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3052000105381012},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.30140000581741333},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.29760000109672546},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.296099990606308},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.29589998722076416},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.2888000011444092},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2831000089645386},{"id":"https://openalex.org/C77660652","wikidata":"https://www.wikidata.org/wiki/Q150971","display_name":"Computer graphics","level":2,"score":0.2802000045776367},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.2703000009059906},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.257099986076355},{"id":"https://openalex.org/C149810388","wikidata":"https://www.wikidata.org/wiki/Q5374873","display_name":"Emulation","level":2,"score":0.25600001215934753},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.25459998846054077},{"id":"https://openalex.org/C66629338","wikidata":"https://www.wikidata.org/wiki/Q189177","display_name":"3D computer graphics","level":3,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.20730","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.20730","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.2604.20730","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.20730","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Multimodal":[0],"Large":[1],"Language":[2],"Models":[3],"(MLLMs)":[4],"have":[5],"shown":[6],"promising":[7],"capabilities":[8],"in":[9,49],"generating":[10],"Scalable":[11],"Vector":[12],"Graphics":[13],"(SVG)":[14],"via":[15],"direct":[16],"code":[17,33,112],"synthesis.":[18],"However,":[19,136],"existing":[20],"paradigms":[21],"typically":[22],"adopt":[23],"an":[24,65],"open-loop":[25],"\"blind":[26],"drawing\"":[27],"approach,":[28],"where":[29],"models":[30,70,147],"generate":[31],"symbolic":[32],"sequences":[34],"without":[35],"perceiving":[36],"intermediate":[37,111,190],"visual":[38,46,124,142,172,191],"outcomes.":[39],"This":[40,224],"methodology":[41],"severely":[42],"underutilizes":[43],"the":[44,118,122,185,221,227],"powerful":[45],"priors":[47],"embedded":[48],"MLLMs":[50],"vision":[51],"encoders,":[52],"treating":[53],"SVG":[54,102],"generation":[55,98,188],"as":[56,104],"a":[57,96,105,115,177,194,212],"disjointed":[58],"textual":[59],"sequence":[60],"modeling":[61],"task":[62],"rather":[63],"than":[64],"integrated":[66],"visuo-spatial":[67],"one.":[68],"Consequently,":[69],"struggle":[71],"to":[72,132,145,151,154,168,183,201],"reason":[73],"about":[74],"partial":[75],"canvas":[76],"states":[77,113],"and":[78,174,205,231,241],"implicit":[79],"occlusion":[80],"relationships,":[81],"which":[82],"are":[83],"visually":[84],"explicit":[85],"but":[86],"textually":[87],"ambiguous.":[88],"To":[89,159],"bridge":[90],"this":[91,141],"gap,":[92],"we":[93,137,162],"propose":[94],"Render-in-the-Loop,":[95],"novel":[97],"paradigm":[99,237],"that":[100,139],"reformulates":[101],"synthesis":[103],"step-wise,":[106],"visual-context-aware":[107],"process.":[108],"By":[109],"rendering":[110],"into":[114],"cumulative":[116],"canvas,":[117],"model":[119],"explicitly":[120],"observes":[121],"evolving":[123],"context":[125],"at":[126],"each":[127],"step,":[128],"leveraging":[129],"on-the-fly":[130],"feedback":[131],"guide":[133],"subsequent":[134],"generation.":[135],"demonstrate":[138],"applying":[140],"loop":[143],"naively":[144],"off-the-shelf":[146],"is":[148,199],"suboptimal":[149],"due":[150],"their":[152],"inability":[153],"leverage":[155],"incremental":[156],"visual-code":[157],"mappings.":[158],"address":[160],"this,":[161],"first":[163],"utilize":[164],"fine-grained":[165],"path":[166],"decomposition":[167],"construct":[169],"dense":[170],"multi-step":[171],"trajectories,":[173],"then":[175],"introduce":[176],"Visual":[178],"Self-Feedback":[179],"(VSF)":[180],"training":[181],"strategy":[182],"condition":[184],"next":[186],"primitive":[187],"on":[189,211,220],"states.":[192],"Furthermore,":[193],"Render-and-Verify":[195],"(RaV)":[196],"inference":[197],"mechanism":[198],"proposed":[200],"effectively":[202],"filter":[203],"degenerate":[204],"redundant":[206],"primitives.":[207],"Our":[208],"framework,":[209],"instantiated":[210],"multimodal":[213],"foundation":[214],"model,":[215],"outperforms":[216],"strong":[217],"open-weight":[218],"baselines":[219],"standard":[222],"MMSVGBench.":[223],"result":[225],"highlights":[226],"remarkable":[228],"data":[229],"efficiency":[230],"generalization":[232],"capability":[233],"of":[234],"our":[235],"Render-in-the-Loop":[236],"for":[238],"both":[239],"Text-to-SVG":[240],"Image-to-SVG":[242],"tasks.":[243]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-04-24T00:00:00"}